© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 9097
    Prev
    Next
    INDEX
    Explanations

    indicators of code structure and flow, such as opening and closing brackets, and specific programming constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    niająca
    -0.53
     Dickerson
    -0.51
    ViewFeatures
    -0.51
    '),
    -0.49
     acyl
    -0.49
    ",
    -0.48
    "),
    -0.47
    CodeAttribute
    -0.47
    spender
    -0.47
    unächst
    -0.46
    POSITIVE LOGITS
    }//
    0.69
    ↵
    0.62
    ↵↵
    0.61
    }/*
    0.59
    getch
    0.57
    ↵↵↵
    0.56
    migrationBuilder
    0.56
    ↵↵↵↵↵↵↵↵↵↵
    0.55
    ↵↵↵↵
    0.55
    ↵↵↵↵↵↵↵↵
    0.52
    Activations Density 0.045%

    No Known Activations