© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 14539
    Prev
    Next
    INDEX
    Explanations

    questions about qualifications, outcomes, and the perceptions of individuals regarding their abilities or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rujuakan
    -0.43
     يتيمه
    -0.42
     unnecessary
    -0.41
    CrossRef
    -0.41
    itoneal
    -0.39
    괜
    -0.38
    meren
    -0.38
    ismet
    -0.37
    aiso
    -0.37
     OPTIONAL
    -0.37
    POSITIVE LOGITS
     cannot
    2.89
    cannot
    2.47
     Cannot
    2.36
    Cannot
    2.20
     couldn
    2.20
     unable
    2.14
     CANNOT
    1.97
     cant
    1.88
     нельзя
    1.88
     Unable
    1.87
    Activations Density 1.639%

    No Known Activations