© 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. 27-GEMMASCOPE-RES-16K
    6. 9274
    Prev
    Next
    INDEX
    Explanations

    code related to data structures and initialization in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stdc
    -0.46
     ProductService
    -0.35
    parseFrom
    -0.35
    
    -0.35
     exposure
    -0.34
    rotta
    -0.34
    vestre
    -0.34
    purl
    -0.33
    AILABILITY
    -0.33
     ""));
    -0.32
    POSITIVE LOGITS
     defaultstate
    0.66
     <<<<<<<<<<<<<<
    0.57
     arreglo
    0.56
     ExecuteAsync
    0.54
     toArray
    0.52
    MigrationBuilder
    0.52
    toArray
    0.51
    Scénario
    0.51
     arrayOf
    0.50
    Jeografia
    0.49
    Activations Density 0.134%

    No Known Activations