© 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. 4-GEMMASCOPE-RES-16K
    6. 3813
    Prev
    Next
    INDEX
    Explanations

    expressions related to requests and commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )");
    
    -0.92
    )";
    
    -0.90
    '):
    
    -0.83
    '))
    
    -0.82
    "):
    
    -0.80
    Rüyada
    -0.80
    %")
    -0.79
    !")
    
    -0.78
    %");
    -0.76
    "))
    
    -0.75
    POSITIVE LOGITS
    Hochspringen
    0.52
    चना
    0.49
     nakalista
    0.48
     Otherwise
    0.47
    VersionUID
    0.46
     otherwise
    0.46
     disposent
    0.46
     оригіналу
    0.45
    tać
    0.45
    SetString
    0.45
    Activations Density 0.234%

    No Known Activations