© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 34-GEMMASCOPE-RES-16K
    6. 8463
    Prev
    Next
    INDEX
    Explanations

    code structure and components related to packages and libraries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     in
    -0.39
     either
    -0.38
     as
    -0.35
     again
    -0.35
     some
    -0.34
     without
    -0.33
     that
    -0.33
     of
    -0.33
     following
    -0.33
     set
    -0.32
    POSITIVE LOGITS
    出版年
    1.17
    <unused43>
    1.12
    <unused42>
    1.11
    <unused41>
    1.11
    <unused47>
    1.11
    <unused51>
    1.11
    <unused17>
    1.11
    <unused3>
    1.10
    [@BOS@]
    1.10
    <pad>
    1.10
    Activations Density 0.146%

    No Known Activations