© 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. 93183
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental and biological contexts

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

    deep vein thrombosis

    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
    +#+#
    -0.65
    delwed
    -0.63
     autorytatywna
    -0.63
    UserScript
    -0.58
    曖昧さ回避
    -0.57
    帖最后由
    -0.54
    出版年
    -0.53
     kasarigan
    -0.52
    haikusbot
    -0.51
     estekak
    -0.51
    POSITIVE LOGITS
     deep
    1.15
     Deep
    1.15
     DEEP
    1.06
    Deep
    1.00
    deep
    0.99
    DEEP
    0.94
     deeper
    0.93
     deepest
    0.93
     depth
    0.92
     deepen
    0.90
    Activations Density 0.019%

    No Known Activations