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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 14274
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual, Ku

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cyfarwyddwr
    -0.46
    IVEREF
    -0.43
    ográficos
    -0.36
    </tfoot>
    -0.33
    ectoria
    -0.33
     ComVisible
    -0.33
     jestli
    -0.33
     Aérea
    -0.32
    StreetMap
    -0.32
     STEVEN
    -0.31
    POSITIVE LOGITS
    ViewFeatures
    0.52
     MonoBehaviour
    0.49
     resourceCulture
    0.46
     KU
    0.45
    期刊论文
    0.45
    awtextra
    0.44
    قایناق‌لار
    0.44
    Ku
    0.44
     ProtoMessage
    0.44
     HasFactory
    0.44
    Activations Density 0.140%

    No Known Activations