© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 425
    Prev
    Next
    INDEX
    Explanations

    code-related constructs, primarily focusing on error handling and function calls

    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
     ['
    -0.66
     ["
    -0.56
    ]-->
    -0.54
    Segments
    -0.54
     totalSupply
    -0.54
     '').
    -0.54
     '**
    -0.53
    '].
    -0.53
     ’
    -0.52
     décidé
    -0.50
    POSITIVE LOGITS
     resourceCulture
    0.97
     autorytatywna
    0.86
    protoimpl
    0.80
     فريبيس
    0.79
     nahilalakip
    0.72
    richTextPanel
    0.71
     houſe
    0.68
    الإنجليزية
    0.68
    Datuak
    0.68
    parsedMessage
    0.66
    Activations Density 0.092%

    No Known Activations