© 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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 104609
    Prev
    Next
    INDEX
    Explanations

    references to processes or procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ulong
    -0.46
    锂
    -0.40
     newName
    -0.40
     Leighton
    -0.39
     vermelhas
    -0.38
    chränk
    -0.37
     namorados
    -0.36
     EUROPEAN
    -0.36
     marinho
    -0.35
     tóxic
    -0.35
    POSITIVE LOGITS
     Process
    0.87
     process
    0.79
    process
    0.76
    NameInMap
    0.76
    Process
    0.74
     PROCESS
    0.73
    策
    0.68
    исленность
    0.66
    ISODE
    0.65
    الحياه
    0.65
    Activations Density 0.014%

    No Known Activations