Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 2926
    Prev
    Next
    INDEX
    Explanations

    technical terms and code-related syntax, particularly in the context of computer programming and system configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    numerical and alphanumeric codes, identifiers, and technical reference markers.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "]);
    
    -0.65
    ")));
    
    -0.64
    ]";
    -0.62
    )"),
    -0.60
    "){
    
    -0.60
    "];
    
    -0.60
    存于互联网档案馆
    -0.59
    )";
    -0.59
    ",@"
    -0.58
    "],
    
    -0.57
    POSITIVE LOGITS
     pylint
    0.50
    InstanceState
    0.47
    jsonwebtoken
    0.46
     disponibilités
    0.46
    🟤
    0.45
    fektions
    0.43
     Dying
    0.42
    onnay
    0.41
    ronpa
    0.41
    findpost
    0.41
    Activations Density 2.439%

    No Known Activations