© 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. 8-GEMMASCOPE-RES-16K
    11. 15245
    Prev
    Next
    INDEX
    Explanations

    terms associated with analysis, evaluation, and rationalization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     confirma
    -0.57
    .
    -0.57
    <eos>
    -0.44
     paying
    -0.43
     earning
    -0.41
     classifica
    -0.41
     transforma
    -0.41
     curing
    -0.40
    される
    -0.40
    йн
    -0.40
    POSITIVE LOGITS
     doubtnut
    0.86
     تانيه
    0.84
    ditor
    0.78
    omány
    0.77
    zdro
    0.76
    ynchronously
    0.75
     itſelf
    0.74
     coö
    0.73
    NewUrlParser
    0.72
     nawr
    0.72
    Activations Density 0.459%

    No Known Activations