© 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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 121750
    Prev
    Next
    INDEX
    Explanations

    references to data shapes and reshaping in arrays or tensors

    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 @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    專
    -0.32
     sticks
    -0.31
    __*/
    -0.31
    {{/
    -0.30
     stick
    -0.30
     zvuky
    -0.29
     Stick
    -0.27
     Kle
    -0.27
     einzelne
    -0.27
    专
    -0.26
    POSITIVE LOGITS
    shape
    2.33
     shape
    1.81
     Shape
    1.71
    Shape
    1.68
    SHAPE
    1.63
     SHAPE
    1.63
    hape
    1.30
    shapes
    1.30
     shapes
    1.24
     Shapes
    1.21
    Activations Density 0.002%

    No Known Activations