© 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. 16-GEMMASCOPE-RES-16K
    11. 9950
    Prev
    Next
    INDEX
    Explanations

    terms related to types of chemical formulations and reactions

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     t
    -0.23
    ty
    -0.23
     meilleurs
    -0.21
     real
    -0.20
    n
    -0.20
    w
    -0.20
     transformed
    -0.20
     relative
    -0.20
    ↵
    -0.19
     pa
    -0.18
    POSITIVE LOGITS
    RTSC
    0.96
    DockStyle
    0.96
     ModelExpression
    0.96
    出版年
    0.92
     zwiſchen
    0.90
    AndEndTag
    0.88
    нгред
    0.88
    <unused17>
    0.88
    <unused41>
    0.87
    <unused43>
    0.87
    Activations Density 0.944%

    No Known Activations