© 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. 34-GEMMASCOPE-RES-16K
    6. 11352
    Prev
    Next
    INDEX
    Explanations

    variables and keywords associated with programming and coding concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "):
    
    -1.42
    "])
    
    -1.41
    "],
    
    -1.41
    '],
    
    -1.34
    ()))
    
    -1.33
    "},
    
    -1.32
    "];
    
    -1.32
    '):
    
    -1.30
    '])
    
    -1.29
    '),
    
    -1.28
    POSITIVE LOGITS
    ?
    0.39
    .
    0.30
     problem
    0.27
     Problem
    0.27
     restantes
    0.27
    kar
    0.26
     communs
    0.26
     devront
    0.26
    gelen
    0.26
    polazione
    0.26
    Activations Density 0.285%

    No Known Activations