© 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. 21-GEMMASCOPE-RES-16K
    11. 2626
    Prev
    Next
    INDEX
    Explanations

    control flow statements and syntax structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.59
     queſta
    -0.54
    ỡng
    -0.53
    GOTREF
    -0.50
    évaluateur
    -0.45
     increí
    -0.45
    MessageTagHelper
    -0.45
    /**
    -0.43
    ViewImports
    -0.43
    PreferredItem
    -0.43
    POSITIVE LOGITS
    elif
    0.66
     anything
    0.61
     else
    0.61
     or
    0.57
     any
    0.52
    elsif
    0.52
    anything
    0.51
     other
    0.51
     if
    0.50
     Anything
    0.49
    Activations Density 0.162%

    No Known Activations