Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 6041
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and judicial proceedings

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

    Numbers followed by other numbers

    np_acts-logits-general · gemini-2.0-flash

    legal citations and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Six
    -0.56
     Nine
    -0.54
     fourth
    -0.54
     fifth
    -0.53
     triple
    -0.53
     Fourth
    -0.52
    4
    -0.52
     Four
    -0.52
     Five
    -0.52
     six
    -0.51
    POSITIVE LOGITS
    aarrggbb
    1.01
     ویکی‌آمباردا
    0.88
    hyrchwyd
    0.82
    UnsafeEnabled
    0.80
    extAlignment
    0.80
     Wikimedijinoj
    0.76
    InjectAttribute
    0.76
    ագրություններ
    0.74
    InitVars
    0.70
     pageable
    0.69
    Activations Density 1.121%

    No Known Activations