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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 53256
    Prev
    Next
    INDEX
    Explanations

    specific references to patents and formal descriptions of processes or innovations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    новништво
    -0.64
    PyExc
    -0.63
    VolleyError
    -0.62
    rungsseite
    -0.60
    ⓧ
    -0.57
     <=",
    -0.57
    enterOuterAlt
    -0.57
    Aktualisiert
    -0.56
     препратки
    -0.55
     transférez
    -0.54
    POSITIVE LOGITS
    man
    0.32
    z
    0.32
    gründ
    0.31
    ppe
    0.31
    able
    0.31
    iele
    0.31
    bre
    0.30
     “
    0.30
    ties
    0.30
    pe
    0.29
    Activations Density 0.171%

    No Known Activations