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-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 3384
    Prev
    Next
    INDEX
    Explanations

    references to sources or citations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    msgTypes
    -0.59
    "}},
    -0.57
    ")){
    
    -0.57
     maniere
    -0.56
    iented
    -0.55
    "—
    -0.53
    IMPORTED
    -0.52
    )—
    -0.52
     ';
    
    -0.50
    &
    
    -0.50
    POSITIVE LOGITS
    Source
    2.23
     Source
    1.75
    SOURCE
    1.40
     SOURCE
    1.32
    source
    1.17
    Fuente
    1.15
     source
    1.12
    ource
    1.08
    منبع
    1.01
    Sumber
    1.01
    Activations Density 0.046%

    No Known Activations