© 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
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 3206
    Prev
    Next
    INDEX
    Explanations

    prominent entertainers and references to their work or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.44
    новништво
    -0.44
    LookAnd
    -0.42
    enderror
    -0.40
     resourceCulture
    -0.40
    IsMutable
    -0.39
    setVerticalGroup
    -0.38
    كويكب
    -0.38
     sélectionnez
    -0.37
    istock
    -0.37
    POSITIVE LOGITS
     Jefus
    0.60
     Inſ
    0.59
     EconPapers
    0.59
     pleaſure
    0.58
     ſch
    0.57
     myſelf
    0.55
     ſta
    0.54
     themſelves
    0.53
     Diſ
    0.52
     reaſon
    0.52
    Activations Density 0.420%

    No Known Activations