© 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-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 14942
    Prev
    Next
    INDEX
    Explanations

    sequences of numerical values and their representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    getMenuInflater
    -0.76
    ViewFeatures
    -0.76
     Efq
    -0.75
    
    -0.74
    DeleteBehavior
    -0.72
    IsContent
    -0.70
     Theſe
    -0.70
    )";
    
    -0.68
     ")";
    -0.68
    borderSide
    -0.67
    POSITIVE LOGITS
     تعدى
    0.61
     alho
    0.46
     vå
    0.45
    inesis
    0.42
     tendremos
    0.40
    ureux
    0.40
    ridae
    0.40
     nau
    0.39
    成
    0.39
    MILLIS
    0.39
    Activations Density 0.068%

    No Known Activations