Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 85792
    Prev
    Next
    INDEX
    Explanations

    occurrences of the opening curly brace character in code snippets

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

    code structures { }

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     alm
    -0.58
     cras
    -0.45
    isOn
    -0.43
     hals
    -0.42
     Alm
    -0.41
     vern
    -0.41
    isman
    -0.40
     integration
    -0.39
     assessment
    -0.39
     perman
    -0.39
    POSITIVE LOGITS
    ({
    0.75
    Disliked
    0.69
     defaultstate
    0.67
    ]={
    0.66
     {
    0.65
     wuß
    0.65
    /**
    0.64
     ibunya
    0.64
     initComponents
    0.64
    []{
    0.64
    Activations Density 0.051%

    No Known Activations