© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 8163
    Prev
    Next
    INDEX
    Explanations

    syntactic structures and code components in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.88
     المعيارى
    -0.82
    Diweddarwch
    -0.82
    DebuggerNonUser
    -0.77
     autorytatywna
    -0.76
    RenderAtEndOf
    -0.75
     propOrder
    -0.75
     Roskov
    -0.74
    Autoritní
    -0.71
    PreInfinity
    -0.70
    POSITIVE LOGITS
     both
    0.65
     ambos
    0.60
     begge
    0.59
    both
    0.59
    Both
    0.57
     båda
    0.54
     beide
    0.53
    Ambos
    0.53
     keduanya
    0.53
     Both
    0.52
    Activations Density 0.468%

    No Known Activations