© 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. 35-GEMMASCOPE-RES-16K
    6. 14063
    Prev
    Next
    INDEX
    Explanations

    terms related to architecture and structural design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.35
     officielles
    -0.33
    kloped
    -0.33
    niec
    -0.32
     vieilles
    -0.31
     statistiques
    -0.31
    RectangleBorder
    -0.31
     científicas
    -0.30
     affitto
    -0.30
    displaymath
    -0.30
    POSITIVE LOGITS
     sculptural
    0.72
     typology
    0.69
     cantile
    0.69
     typo
    0.68
     programmatic
    0.68
    SharedCtor
    0.64
     interstitial
    0.60
    typo
    0.60
     articulation
    0.60
     circulation
    0.60
    Activations Density 0.183%

    No Known Activations