© 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. 14-GEMMASCOPE-RES-16K
    11. 5333
    Prev
    Next
    INDEX
    Explanations

    expressions related to initialization and configuration of variables or data structures

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    wikimedia
    -0.38
    freopen
    -0.35
     Moose
    -0.34
     TUS
    -0.33
    }>
    -0.33
     revi
    -0.33
     ber
    -0.33
    Teng
    -0.32
     CreateTagHelper
    -0.32
     než
    -0.32
    POSITIVE LOGITS
    ThroughAttribute
    0.76
    omitempty
    0.63
    parsedMessage
    0.58
    RepeatedField
    0.57
    complexContent
    0.57
     незавершена
    0.56
    RefNanny
    0.56
    titleMargin
    0.54
    grimas
    0.53
     mergeFrom
    0.53
    Activations Density 0.149%

    No Known Activations