© 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. 7-GEMMASCOPE-RES-16K
    11. 16078
    Prev
    Next
    INDEX
    Explanations

    references to initial or significant experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ptures
    -0.37
    enumi
    -0.35
    [...,
    -0.34
    randomUUID
    -0.34
     lemn
    -0.33
    skapet
    -0.33
     câte
    -0.32
     actualidad
    -0.31
    celotti
    -0.31
     globos
    -0.31
    POSITIVE LOGITS
     first
    1.02
     eerste
    0.90
    first
    0.86
     earliest
    0.86
     primeiras
    0.85
     erste
    0.85
     ersten
    0.84
     pertama
    0.83
     FIRST
    0.82
     first
    0.81
    Activations Density 0.295%

    No Known Activations