© 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. 19960
    Prev
    Next
    INDEX
    Explanations

    references to tiles in various contexts

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

    tilejson

    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
    cstdio
    -0.42
    sidemargin
    -0.40
    s
    -0.39
     Freedman
    -0.34
    kans
    -0.34
     HEP
    -0.33
     Autorisations
    -0.33
    nya
    -0.33
     Beck
    -0.32
    ための
    -0.32
    POSITIVE LOGITS
    Tile
    2.67
     Tile
    2.59
    tile
    2.50
     tile
    2.48
     TILE
    2.09
    TILE
    1.88
     tiles
    1.63
     Tiles
    1.56
    tiles
    1.45
    Tiles
    1.41
    Activations Density 0.005%

    No Known Activations