© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 14024
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to logistics and administrative details

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

    financial and service terms

    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
     serem
    -0.28
     Pourtant
    -0.27
     supposed
    -0.26
     because
    -0.25
     pourtant
    -0.25
     gewesen
    -0.22
     justement
    -0.21
     zase
    -0.21
     fueran
    -0.20
    <i>
    -0.20
    POSITIVE LOGITS
     Chwiliwch
    0.96
    ðsíða
    0.94
    majánló
    0.94
    OGND
    0.93
    yntaxException
    0.93
     Италијани
    0.93
    ésultats
    0.93
    <pad>
    0.92
     ivelany
    0.92
    <unused3>
    0.91
    Activations Density 0.067%

    No Known Activations