© 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. 16-GEMMASCOPE-RES-16K
    11. 14580
    Prev
    Next
    INDEX
    Explanations

    language related to privacy policies and user consent

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

    Follows pronouns or the word "to"

    np_acts-logits-general · gemini-2.0-flash

    your request or opening sequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.57
    ...
    -0.54
     Meyer
    -0.54
     ha
    -0.50
    …
    -0.50
    initState
    -0.49
     tiro
    -0.49
     r
    -0.49
     plus
    -0.47
     Smith
    -0.46
    POSITIVE LOGITS
     itſelf
    0.91
     ſind
    0.84
     ―――――
    0.83
     raiſ
    0.83
     myſelf
    0.81
    出版年
    0.81
     ſeveral
    0.81
     reaſon
    0.79
     Reſ
    0.79
     ་་
    0.78
    Activations Density 0.291%

    No Known Activations