© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 91090
    Prev
    Next
    INDEX
    Explanations

    references to forces and their directional properties in mechanical systems

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

    inward and outward directions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jspx
    -0.29
    saraba
    -0.28
    PreferredItem
    -0.28
    MLLoader
    -0.26
    oa̍t
    -0.26
    WriteBarrier
    -0.25
     gynhyrchwyd
    -0.25
    googleapis
    -0.25
     AUSSI
    -0.25
    BeginContext
    -0.24
    POSITIVE LOGITS
     inward
    1.70
     inwards
    1.67
     outwards
    1.65
     outward
    1.61
     towards
    1.43
     toward
    1.39
     hacia
    1.32
    towards
    1.29
     Towards
    1.27
     inwardly
    1.25
    Activations Density 0.130%

    No Known Activations