© 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. 3-GEMMASCOPE-RES-16K
    11. 6152
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to scientific processes or methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Geſch
    -0.74
    rogels
    -0.72
    yelidikan
    -0.68
    ähteet
    -0.67
    <bos>
    -0.65
    ੝
    -0.64
    󠁣
    -0.61
     Bewußt
    -0.60
    genodigd
    -0.60
     Menschheit
    -0.59
    POSITIVE LOGITS
     pro
    0.44
     base
    0.42
    دانشنامهٔ
    0.41
    DeleteBehavior
    0.41
    detectChanges
    0.41
     cas
    0.41
     super
    0.41
     prop
    0.40
     
    0.39
     can
    0.38
    Activations Density 10.881%

    No Known Activations