© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 20145
    Prev
    Next
    INDEX
    Explanations

    references to statistical significance and methodology related to study design

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

    causes and effects

    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
     avulla
    -0.47
     помогают
    -0.46
    帮助
    -0.45
     sayesinde
    -0.45
     helfen
    -0.44
     enable
    -0.42
    帮你
    -0.41
     помогут
    -0.41
     благода
    -0.40
     помогает
    -0.40
    POSITIVE LOGITS
     causing
    1.38
     menyebabkan
    1.18
    causing
    1.16
     mengakibatkan
    1.15
    導致
    1.09
     causando
    1.06
     causes
    1.06
    导致
    1.04
    causes
    1.01
     threatens
    0.99
    Activations Density 0.729%

    No Known Activations