© 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. 16-GEMMASCOPE-RES-16K
    11. 9677
    Prev
    Next
    INDEX
    Explanations

    segments of code or technical parameters related to data structures or functions in programming

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    RenderAtEndOf
    -1.20
    iſen
    -1.09
     queſta
    -1.07
     defaultstate
    -1.03
    IntoConstraints
    -1.02
    OGND
    -1.00
    ſicht
    -1.00
    ロウィン
    -0.98
    SequentialGroup
    -0.97
     للاسماء
    -0.96
    POSITIVE LOGITS
    1
    0.54
    0
    0.48
    [toxicity=0]
    0.47
    Of
    0.45
    The
    0.45
    A
    0.44
    2
    0.44
    (
    0.44
    I
    0.44
    9
    0.41
    Activations Density 0.005%

    No Known Activations