© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 10360
    Prev
    Next
    INDEX
    Explanations

    references to discussions and opinions related to shared ideas or comments

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    열
    -0.35
    ardar
    -0.35
    parseLong
    -0.34
     []).
    -0.34
    BaseAdapter
    -0.34
    rungsseite
    -0.34
     hopp
    -0.34
     eno
    -0.33
     capri
    -0.33
    企
    -0.33
    POSITIVE LOGITS
    findpost
    0.47
    IsMutable
    0.47
    delwed
    0.47
     насељу
    0.46
    StructEnd
    0.44
    ngths
    0.43
     vocês
    0.42
     acima
    0.42
    ChildIndex
    0.40
    utuhkan
    0.40
    Activations Density 0.316%

    No Known Activations