© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 122642
    Prev
    Next
    INDEX
    Explanations

    key names and proper nouns related to specific cultural references, products, or individuals

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

    .com websites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    UnusedPrivate
    -0.80
     CreateTagHelper
    -0.79
     AssemblyTitle
    -0.64
    graphiques
    -0.62
    hoeddwyd
    -0.58
    tanleria
    -0.58
    Dislikes
    -0.58
     تانيه
    -0.57
    afficheront
    -0.56
     Roskov
    -0.54
    POSITIVE LOGITS
     sumpay
    0.41
    !
    0.38
    Cordialement
    0.37
    !”
    0.36
    WriteBarrier
    0.34
     Exactos
    0.33
    <eos>
    0.32
     dormitórios
    0.32
    Parabéns
    0.31
     contín
    0.31
    Activations Density 0.022%

    No Known Activations