© 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. 21-GEMMASCOPE-RES-16K
    11. 6247
    Prev
    Next
    INDEX
    Explanations

    questions that start with "Where"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    numerusform
    -0.61
    锈钢
    -0.57
    ={`/
    -0.56
    ity
    -0.56
     GridLayout
    -0.56
     invokingState
    -0.54
     dlaczego
    -0.53
    ième
    -0.53
    MessageTagHelper
    -0.53
    IntoConstraints
    -0.52
    POSITIVE LOGITS
     else
    1.04
    ever
    0.93
    unto
    0.80
    upon
    0.80
    quiera
    0.77
     they
    0.73
    fores
    0.72
    bouts
    0.69
     Où
    0.69
     Else
    0.68
    Activations Density 0.074%

    No Known Activations