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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 32-GEMMASCOPE-RES-131K
    6. 129940
    Prev
    Next
    INDEX
    Explanations

    references to enclosures or containing structures

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

    enclosed or enclosure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.32.hook_resid_post
    Hook Layer
    32
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    truly
    -0.48
    iri
    -0.48
    thyst
    -0.42
    Truly
    -0.42
    archiviato
    -0.42
    Darth
    -0.42
    ApiProperty
    -0.42
    setopt
    -0.41
    ibase
    -0.41
    sendKeys
    -0.40
    POSITIVE LOGITS
     praça
    0.56
    aperto
    0.52
    LookAnd
    0.52
     plegable
    0.48
     चीज़ों
    0.48
     jaula
    0.48
     cappello
    0.46
     cervello
    0.45
     ProtoMessage
    0.45
    IntoConstraints
    0.45
    Activations Density 0.012%

    No Known Activations