© 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. 12062
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs related to children elements in a data structure

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

    user input

    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
     المعيارى
    -0.64
    |};
    -0.62
    ]]);
    -0.52
    WriteTagHelper
    -0.51
    دانشنامهٔ
    -0.51
     للاسماء
    -0.50
     ModelExpression
    -0.49
    "]=
    -0.49
    }}},
    -0.49
     صوتيه
    -0.47
    POSITIVE LOGITS
     as
    0.96
     sebagai
    0.87
    为例
    0.73
     ως
    0.66
    作为
    0.59
     Sebagai
    0.57
     как
    0.56
    sebagai
    0.55
     kao
    0.54
     як
    0.54
    Activations Density 0.003%

    No Known Activations