© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 10748
    Prev
    Next
    INDEX
    Explanations

    references to people involved in significant events or actions

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

    the definite article "the" appearing in formal or technical contexts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.95
    bootstrapcdn
    -0.88
    verwijspagina
    -0.79
    rungsseite
    -0.79
    ReusableCell
    -0.75
    BeginContext
    -0.73
     queſta
    -0.72
    ðsíða
    -0.71
    RTEE
    -0.69
    ſchaft
    -0.69
    POSITIVE LOGITS
     tersebut
    0.45
     dicha
    0.43
    </strong>
    0.43
     said
    0.41
    <h1>
    0.40
    </h1>
    0.37
    <
    0.35
    </h5>
    0.35
     citada
    0.34
    enumi
    0.34
    Activations Density 0.918%

    No Known Activations