© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 84555
    Prev
    Next
    INDEX
    Explanations

    proper nouns or specific names, particularly related to music and literature

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

    Metallica, Verlag, Eastwood, ReadFile, rubin, Family

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.60
    ]")]
    -0.60
    GTCX
    -0.52
     aDecoder
    -0.52
    WriteTagHelper
    -0.52
     noft
    -0.50
    SharedCtor
    -0.48
     zijne
    -0.47
     chré
    -0.47
     disambiguazione
    -0.47
    POSITIVE LOGITS
     ModelExpression
    0.60
     Metallica
    0.59
    Metallica
    0.51
    ondissement
    0.50
    rubin
    0.48
    tagHelper
    0.42
    SqlSession
    0.41
    upol
    0.40
    LookAndFeel
    0.40
    NamedQueries
    0.39
    Activations Density 0.004%

    No Known Activations