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

    Neuronpedia

    Jacobian LensNEW
    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. 16-GEMMASCOPE-RES-16K
    11. 12330
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to structure and architecture in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    posedge
    -0.62
     Aprend
    -0.50
     Ney
    -0.46
    gratis
    -0.45
     ואת
    -0.44
    obut
    -0.44
    paid
    -0.44
     nguy
    -0.43
    횟
    -0.43
    Katso
    -0.43
    POSITIVE LOGITS
     structure
    1.38
     Structure
    1.38
    structure
    1.31
     STRUCTURE
    1.25
    Structure
    1.24
    STRUCTURE
    1.13
     struttura
    1.13
     Structures
    1.10
     structures
    1.06
     struktur
    1.03
    Activations Density 0.125%

    No Known Activations