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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 273
    Prev
    Next
    INDEX
    Explanations

    the occurrence of specific variable or class names in code-like structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "):
    
    -0.81
    )");
    
    -0.80
    "]];
    -0.78
    "])
    
    -0.76
    -",
    -0.75
    )”.
    -0.74
    %");
    -0.72
    llllllll
    -0.71
    "+
    
    -0.71
    )".
    -0.69
    POSITIVE LOGITS
    __
    1.76
     (!__
    0.82
    --
    0.82
    &__
    0.80
    FormTagHelper
    0.76
    __.
    0.74
    ___
    0.71
     Caw
    0.71
     Kershaw
    0.71
     coupler
    0.70
    Activations Density 0.089%

    No Known Activations