© 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. 23-GEMMASCOPE-RES-16K
    6. 2202
    Prev
    Next
    INDEX
    Explanations

    references to documents or written communications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.67
     kasarigan
    -0.56
    
    -0.51
    onOptions
    -0.48
    onViewCreated
    -0.48
    awtextra
    -0.47
    IMPORTED
    -0.46
    AutoScaleMode
    -0.46
     autorytatywna
    -0.46
    bootstrapcdn
    -0.46
    POSITIVE LOGITS
    riwal
    0.57
    новништво
    0.54
     was
    0.46
     которое
    0.44
     והוא
    0.43
     hacerlo
    0.41
     мәкал
    0.41
    rxjs
    0.40
     він
    0.39
    mayın
    0.39
    Activations Density 0.860%

    No Known Activations