© 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. 1051
    Prev
    Next
    INDEX
    Explanations

    questions and statements relating to choices and decisions

    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
    ThroughAttribute
    -0.63
     resourceCulture
    -0.56
    RegressionTest
    -0.54
    Obrázky
    -0.54
    ExtendWith
    -0.47
    StoryboardSegue
    -0.46
    PerformLayout
    -0.44
     defaultstate
    -0.44
    SuspendLayout
    -0.44
    Referencie
    -0.44
    POSITIVE LOGITS
     make
    3.00
     making
    2.81
    make
    2.78
     Make
    2.66
     makes
    2.64
    Make
    2.61
     Making
    2.50
    Making
    2.48
     MAKE
    2.45
    making
    2.42
    Activations Density 3.194%

    No Known Activations