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. 113513
    Prev
    Next
    INDEX
    Explanations

    references to methods and conditions related to chemical reactions in a laboratory setting

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

    laboratory procedures, equipment, and synthesis

    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
    :✨
    -0.51
     kasarigan
    -0.50
     otomatig
    -0.46
    rungsseite
    -0.46
     resourceCulture
    -0.44
     chi̍t
    -0.44
    stateProvider
    -0.44
     BytesLike
    -0.43
    Referanser
    -0.43
    adaptiveStyles
    -0.43
    POSITIVE LOGITS
    evich
    0.41
    cair
    0.41
    orsese
    0.37
    [],
    0.36
    __).
    0.34
    cached
    0.34
    SPA
    0.34
    tojas
    0.34
    lake
    0.33
    []);
    0.33
    Activations Density 0.126%

    No Known Activations