© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 2863
    Prev
    Next
    INDEX
    Explanations

    legal terms and conditions related to copyright and licensing

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

    copyright and license disclaimers in code comments.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Diweddarwch
    -0.64
    transQ
    -0.58
     ब्रेकडाउन
    -0.53
     informée
    -0.50
    fromnode
    -0.50
     EconPapers
    -0.50
     المعيارى
    -0.49
    asteroide
    -0.49
    Портали
    -0.48
     MainAxisSize
    -0.48
    POSITIVE LOGITS
    TokenNameCOMMA
    0.50
     שוליים
    0.46
    ValueStyle
    0.45
    awtextra
    0.43
    ,:
    0.43
     חיצוניים
    0.43
    ,-
    0.39
    interopRequire
    0.39
    ,;
    0.39
    ,..
    0.38
    Activations Density 1.047%

    No Known Activations