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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 944
    Prev
    Next
    INDEX
    Explanations

    elements related to transportation logistics and connections

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

    connections and junctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DeleteBehavior
    -0.60
     NSCoder
    -0.50
    ⎧
    -0.49
     ModelExpression
    -0.46
    webElement
    -0.45
    expandindo
    -0.44
    ngdoc
    -0.44
    ///**
    -0.42
    Jeografia
    -0.40
    AutoField
    -0.40
    POSITIVE LOGITS
     gawas
    0.50
     Outside
    0.41
     Junction
    0.39
    exits
    0.39
    Junction
    0.39
    Outside
    0.38
     junctions
    0.38
    outside
    0.37
     exit
    0.37
     Exit
    0.37
    Activations Density 0.092%

    No Known Activations