© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 249
    Prev
    Next
    INDEX
    Explanations

    phrases related to direct interaction or connections

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

    direct relationship or evidence

    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
     Economía
    -0.66
     meisje
    -0.61
    pecabe
    -0.61
    덟
    -0.58
     précé
    -0.55
     turística
    -0.55
     Theſe
    -0.54
     newName
    -0.54
     présidenti
    -0.53
     šk
    -0.53
    POSITIVE LOGITS
     direct
    1.19
    direct
    1.16
     Direct
    1.10
    Direct
    1.09
     DIRECT
    1.02
    DIRECT
    0.91
     directly
    0.85
    irect
    0.85
    直接
    0.82
     directo
    0.78
    Activations Density 0.020%

    No Known Activations