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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15753
    Prev
    Next
    INDEX
    Explanations

    references to gift-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.48
    henswürdigkeiten
    -0.47
    UnusedPrivate
    -0.46
    queryInterface
    -0.45
    createStatement
    -0.44
    vician
    -0.43
     IBOutlet
    -0.43
     kohdetta
    -0.42
     oprot
    -0.42
     doInBackground
    -0.42
    POSITIVE LOGITS
     packaging
    0.84
     Packaging
    0.75
    packaging
    0.68
    Packaging
    0.68
     Verpackung
    0.60
     envelopes
    0.56
    pakking
    0.56
     emballage
    0.55
     embalaje
    0.52
     cardboard
    0.52
    Activations Density 0.354%

    No Known Activations