Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 113337
    Prev
    Next
    INDEX
    Explanations

    punctuation and special characters in the document

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

    links and citations

    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
    ValueStyle
    -0.59
    pulseira
    -0.50
     समीक्षक
    -0.49
     RIPRODUZIONE
    -0.48
    存于互联网档案馆
    -0.47
    IContainer
    -0.47
     čierna
    -0.46
     يتيمه
    -0.46
     saveiro
    -0.45
    PostInfinity
    -0.44
    POSITIVE LOGITS
    prüche
    0.60
    Referencies
    0.56
    Legături
    0.51
    Viited
    0.45
    lost
    0.44
     Dodd
    0.43
     LOST
    0.43
     lost
    0.42
     Rh
    0.42
    Karol
    0.42
    Activations Density 0.185%

    No Known Activations