© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 39-GEMMASCOPE-RES-16K
    11. 4401
    Prev
    Next
    INDEX
    Explanations

    references to product and project components in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bė
    -0.26
     "}";
    -0.25
     AspNetCore
    -0.23
     GlobalKey
    -0.23
    ForValue
    -0.23
     Chwiliwch
    -0.23
    ברס
    -0.22
     imageNamed
    -0.22
     espar
    -0.22
    enskap
    -0.21
    POSITIVE LOGITS
     Detail
    0.79
    management
    0.78
     detail
    0.78
     Management
    0.77
    脚注の使い方
    0.75
    detail
    0.75
    Management
    0.75
     management
    0.75
    esModule
    0.72
    mgmt
    0.72
    Activations Density 0.483%

    No Known Activations