© 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. 110717
    Prev
    Next
    INDEX
    Explanations

    descriptions of shapes and forms in various contexts

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

    shape

    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
     propOrder
    -0.65
     bParam
    -0.43
    NOPQRST
    -0.40
     ویکی‌پدی
    -0.38
    BASEPATH
    -0.35
     tickets
    -0.35
     consectetur
    -0.35
     հղումներ
    -0.35
    发表于
    -0.35
    =$((
    -0.34
    POSITIVE LOGITS
     shape
    2.36
     shapes
    2.02
    shape
    2.00
     Shape
    1.97
    Shape
    1.87
     SHAPE
    1.75
    SHAPE
    1.70
     shaped
    1.66
    shapes
    1.65
     Shapes
    1.63
    Activations Density 0.128%

    No Known Activations