© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104763
    Prev
    Next
    INDEX
    Explanations

    references to distances and travel times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     kasarigan
    -0.58
     ExecuteAsync
    -0.53
    LookAnd
    -0.48
    slidesPer
    -0.48
    ußt
    -0.47
    HomeAsUpEnabled
    -0.45
     paſſ
    -0.45
     Dernière
    -0.44
     valentín
    -0.43
    RITION
    -0.43
    POSITIVE LOGITS
     away
    0.48
    Soon
    0.46
    IContainer
    0.44
    soon
    0.44
    GOTREF
    0.41
     Soon
    0.41
    far
    0.39
    ArgumentParser
    0.38
    seits
    0.38
     novia
    0.38
    Activations Density 0.004%

    No Known Activations