© 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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 3494
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the introduction or context of various statements, particularly those that start discussions or explanations

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

    the word "In" at the beginning of sentences or clauses.

    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
    Хьажоргаш
    -0.62
    rungsseite
    -0.59
     argint
    -0.58
    󠁣
    -0.58
    verwijspagina
    -0.55
     autorytatywna
    -0.53
    Vidite
    -0.53
    ThroughAttribute
    -0.52
    IsContent
    -0.52
    ftagPool
    -0.50
    POSITIVE LOGITS
    ostante
    0.67
    quele
    0.62
    selves
    0.61
    hogy
    0.60
    selbe
    0.54
    however
    0.54
    neath
    0.53
    irs
    0.53
    Of
    0.53
    kelt
    0.53
    Activations Density 1.735%

    No Known Activations