© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 39-GEMMASCOPE-RES-16K
    6. 2214
    Prev
    Next
    INDEX
    Explanations

    descriptions of figures and their components in a model or design context

    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
     Vorles
    -0.29
     réforme
    -0.29
     biologique
    -0.29
     Forman
    -0.28
     trekken
    -0.28
     législation
    -0.27
    heiz
    -0.27
     enf
    -0.27
     Komponist
    -0.27
     paroisse
    -0.26
    POSITIVE LOGITS
     decals
    0.90
     styrene
    0.81
     Scale
    0.80
     decal
    0.79
     scale
    0.76
     modeller
    0.73
    Scale
    0.72
     modell
    0.72
     weathering
    0.71
    decal
    0.70
    Activations Density 0.171%

    No Known Activations