© 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. 22-GEMMASCOPE-RES-16K
    11. 10824
    Prev
    Next
    INDEX
    Explanations

    references to input and output in relation to parameters and methods within code

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

    Tokens after "input" and "Input"

    np_acts-logits-general · gemini-2.0-flash

    input operations and parameters

    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
    SharedCtor
    -0.85
     initComponents
    -0.68
     HasFactory
    -0.67
    Parcelize
    -0.65
    CppMethod
    -0.63
    WebServlet
    -0.61
    saraba
    -0.60
     jorden
    -0.59
    ⓘ
    -0.59
     Administrativna
    -0.58
    POSITIVE LOGITS
    ting
    0.74
    ted
    0.69
    output
    0.68
    Output
    0.65
     Output
    0.63
    OUTPUT
    0.61
    输出
    0.57
    setInput
    0.53
    pement
    0.52
     ports
    0.52
    Activations Density 0.113%

    No Known Activations