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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 5877
    Prev
    Next
    INDEX
    Explanations

    references to legal or systemic processes involving justice or authority

    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
     Ebers
    -0.56
     opérateur
    -0.54
     superposition
    -0.53
    Sementara
    -0.52
     sekal
    -0.52
     pagrind
    -0.50
     acreditar
    -0.50
    例文
    -0.49
    pendidikan
    -0.49
    retty
    -0.48
    POSITIVE LOGITS
    awtextra
    0.79
    featureID
    0.76
    encodeWith
    0.74
    contentLoaded
    0.73
    AndEndTag
    0.73
    ViewFeatures
    0.70
    SequentialGroup
    0.70
    XmlAccessType
    0.70
     oprot
    0.68
     kaynağından
    0.67
    Activations Density 0.246%

    No Known Activations