© 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-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 447
    Prev
    Next
    INDEX
    Explanations

    elements related to trials and medical studies, including parameters, participants, and statistical analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portail
    -0.67
    UnusedPrivate
    -0.57
    最快更新
    -0.54
    Eloquent
    -0.52
    reportWebVitals
    -0.50
    KommentareTeilen
    -0.50
    RIZ
    -0.49
     HasFactory
    -0.49
    devamını
    -0.48
     augus
    -0.47
    POSITIVE LOGITS
    prefixer
    0.59
    ไหน
    0.57
     Jurí
    0.57
    LookAnd
    0.54
     ivelany
    0.53
    mybatisplus
    0.53
    oplayer
    0.51
    Chim
    0.51
    oredCriteria
    0.51
     jurídico
    0.51
    Activations Density 7.204%

    No Known Activations