© 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. 40-GEMMASCOPE-RES-16K
    6. 1350
    Prev
    Next
    INDEX
    Explanations

    elements related to JavaScript object properties and their descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "";
    
    -0.57
    ="";
    
    -0.55
     '';
    
    -0.54
    +#+
    -0.52
     "",
    
    -0.52
     "");
    
    -0.51
    帖最后由
    -0.50
    tonode
    -0.50
     '',
    
    -0.50
     @"/
    -0.49
    POSITIVE LOGITS
     Object
    0.54
    Object
    0.51
    extend
    0.49
    Extend
    0.42
     solches
    0.38
    そんな
    0.36
    merge
    0.36
    出版年
    0.36
     Besitz
    0.36
     Objekt
    0.36
    Activations Density 0.243%

    No Known Activations