© 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. 23-GEMMASCOPE-RES-16K
    6. 6926
    Prev
    Next
    INDEX
    Explanations

    parameters and values in programming or configuration files

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    archiviato
    -0.57
     Perſ
    -0.57
    LookAnd
    -0.56
     enfans
    -0.55
     ſtate
    -0.54
     NSCoder
    -0.54
    CDCl
    -0.54
     Monfieur
    -0.50
     referrerpolicy
    -0.49
     juſ
    -0.49
    POSITIVE LOGITS
    alt
    0.40
    ency
    0.39
    offen
    0.38
    anager
    0.37
    toff
    0.37
    astify
    0.36
    beste
    0.36
    own
    0.36
    erapeutics
    0.35
     돌
    0.35
    Activations Density 0.672%

    No Known Activations