© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8218
    Prev
    Next
    INDEX
    Explanations

    phrases or constructions indicating a direct address to the reader, particularly using "you" or "if you" in contexts that suggest offering assistance, instructions, or options to the reader.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    specific user interaction requests or notifications.

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    information related to shipping and technical instructions.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    Followed by intent, questions, or conditions

    np_acts-logits-general · gemini-2.0-flash

    you considering options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.84
    
    -0.77
    tagHelperRunner
    -0.76
    ArgsConstructor
    -0.73
    GEBURTSDATUM
    -0.72
    AsUp
    -0.70
    NOPQRST
    -0.67
    PreferredItem
    -0.66
    principalColumn
    -0.65
    rawDesc
    -0.64
    POSITIVE LOGITS
     plan
    0.74
     decide
    0.72
     intend
    0.66
     ever
    0.59
     opt
    0.59
     forget
    0.59
     accidentally
    0.58
     vergessen
    0.57
     inadvertently
    0.57
    计划
    0.56
    Activations Density 0.208%

    No Known Activations