© 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. 8669
    Prev
    Next
    INDEX
    Explanations

    specific keywords related to data access methods and their implications in various contexts

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

    Followed by "of," "or," "and," or punctuation

    np_acts-logits-general · gemini-2.0-flash

    depending on type

    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
    rawDesc
    -0.57
     سكانية
    -0.55
     TResult
    -0.55
     NSCoder
    -0.52
    IonicModule
    -0.51
    EDEFAULT
    -0.51
    ranton
    -0.50
    ể
    -0.49
    urably
    -0.48
    irms
    -0.48
    POSITIVE LOGITS
     type
    0.82
     whether
    0.70
    whether
    0.65
     tipo
    0.61
     Whether
    0.61
    type
    0.60
    是否是
    0.59
     Тип
    0.59
    类型
    0.58
     types
    0.57
    Activations Density 0.494%

    No Known Activations