© 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. 2357
    Prev
    Next
    INDEX
    Explanations

    code structure and assertions in programming contexts

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

    code-related programming constructs like object property descriptors, assertions, and programming test cases.

    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
     afgelopen
    -0.41
     ytterligare
    -0.34
     populaires
    -0.32
     anledning
    -0.30
     senaste
    -0.30
     мәкал
    -0.29
     recientemente
    -0.29
     polski
    -0.27
     ejemplos
    -0.27
     détail
    -0.27
    POSITIVE LOGITS
    AnchorStyles
    0.75
    Portail
    0.69
    ndor
    0.62
    irms
    0.62
    NameInMap
    0.61
     Vee
    0.60
    Vee
    0.60
    niſſe
    0.59
    ubar
    0.59
     Waray
    0.59
    Activations Density 0.260%

    No Known Activations