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. 10-GEMMASCOPE-RES-16K
    6. 2734
    Prev
    Next
    INDEX
    Explanations

    references to null values and absence of data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __*/
    -0.99
    fromnode
    -0.97
    [])
    
    -0.95
    LookAnd
    -0.94
    __':
    
    -0.93
    "),
    
    -0.92
    "):
    
    -0.91
    AutoScaleMode
    -0.91
    adaptiveStyles
    -0.86
    **/
    
    -0.85
    POSITIVE LOGITS
    .
    0.69
     crystall
    0.65
    ;
    0.56
     Deportes
    0.54
    ArgsConstructor
    0.52
    Configurer
    0.47
    bentar
    0.46
     představ
    0.46
     sinner
    0.46
     flocc
    0.45
    Activations Density 0.115%

    No Known Activations