© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10748
    Prev
    Next
    INDEX
    Explanations

    references to games, specifically video games and their mechanics or dynamics

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

    Code snippets or unusual characters

    np_acts-logits-general · gemini-2.0-flash

    game tactics and names

    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
    DoubleQuotes
    -0.64
     actionPerformed
    -0.45
     OBB
    -0.45
     Petra
    -0.44
    FunctionType
    -0.42
    RTDA
    -0.42
    wezi
    -0.41
     đào
    -0.40
     Marry
    -0.40
    isEmail
    -0.40
    POSITIVE LOGITS
     League
    0.93
    League
    0.81
    ########.
    0.80
    ReusableCell
    0.78
     champions
    0.74
    champion
    0.74
     champion
    0.73
    yntaxException
    0.69
    ագրություններ
    0.68
     LEC
    0.67
    Activations Density 0.092%

    No Known Activations