© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 583
    Prev
    Next
    INDEX
    Explanations

    template and typename declarations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    C++ template and code-related syntax elements like typename, class, and template parameters.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     status
    -0.31
    skjaer
    -0.30
    UnusedPrivate
    -0.30
     total
    -0.29
     Updated
    -0.28
     paj
    -0.28
    ſes
    -0.28
     statut
    -0.28
     ricos
    -0.27
     latar
    -0.27
    POSITIVE LOGITS
    typeparam
    0.89
    تقاوى
    0.69
    ImageContext
    0.67
     autorytatywna
    0.65
    matchCondition
    0.64
    ValueStyle
    0.63
     незавершена
    0.62
     localObject
    0.62
    ंदीखरीदारी
    0.59
    argout
    0.59
    Activations Density 0.113%

    No Known Activations