© 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. 5336
    Prev
    Next
    INDEX
    Explanations

    words indicating necessity, obligation, or condition

    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
     
    -0.34
     G
    -0.30
     Assembly
    -0.29
     v
    -0.28
     P
    -0.28
     I
    -0.28
     R
    -0.28
     gedacht
    -0.28
    </blockquote>
    -0.28
     these
    -0.28
    POSITIVE LOGITS
    ंदीखरीदारी
    0.98
    LookAnd
    0.93
     <<<<<<<<<<<<<<
    0.86
     мәкал
    0.86
    TypedDataSet
    0.85
     nahilalakip
    0.84
     kasarigan
    0.82
    uxxxx
    0.80
     '{@
    0.77
    évaluateur
    0.77
    Activations Density 0.601%

    No Known Activations