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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 12721
    Prev
    Next
    INDEX
    Explanations

    elements related to academic references or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Autorizaciones
    -0.69
    BibitemShut
    -0.68
    addCriterion
    -0.63
    RenderAtEndOf
    -0.63
     незавершена
    -0.62
     >=",
    -0.62
     resourceCulture
    -0.60
    ésultats
    -0.60
    acters
    -0.60
     ''.
    -0.59
    POSITIVE LOGITS
    1
    0.78
     Eleventh
    0.42
     Ilmu
    0.42
     eleven
    0.40
     Eleven
    0.40
    1
    0.37
    १
    0.37
    Eleven
    0.36
     OkHttpClient
    0.36
    イレ
    0.35
    Activations Density 0.590%

    No Known Activations