Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1809
    Prev
    Next
    INDEX
    Explanations

    questions seeking guidance or advice on various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.48
    tvguidetime
    -0.43
     osten
    -0.42
     social
    -0.42
    ❋
    -0.41
     yoke
    -0.40
    Klar
    -0.40
    Prior
    -0.39
     superint
    -0.39
     Bajos
    -0.38
    POSITIVE LOGITS
     виправивши
    1.03
     مواليد
    0.75
     ویکی‌پدیا
    0.71
     commerciaux
    0.68
     recommandé
    0.66
    ManagedBean
    0.65
    دانشنامهٔ
    0.65
    ברס
    0.63
    RegressionTest
    0.63
    ✨:
    0.63
    Activations Density 0.326%

    No Known Activations