© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 42290
    Prev
    Next
    INDEX
    Explanations

    elements related to academic authorship and citations

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

    metadata creation time and title

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     authors
    -0.63
     AUTHORS
    -0.62
    作者
    -0.61
    Personendaten
    -0.60
    WireFormat
    -0.59
     Authors
    -0.58
     nahilalakip
    -0.58
    Authors
    -0.58
     author
    -0.58
    createdBy
    -0.58
    POSITIVE LOGITS
    getKeyCode
    0.39
     date
    0.37
    最快更新
    0.33
    アシ
    0.33
     cím
    0.33
     smtplib
    0.32
     dátum
    0.32
    他们的
    0.31
     venue
    0.31
     betegs
    0.29
    Activations Density 0.025%

    No Known Activations