© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 4238
    Prev
    Next
    INDEX
    Explanations

    expressions indicating positive experiences or feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    positive emotional expressions and sentiments of enthusiasm or satisfaction.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iettes
    -0.47
    hyrchwyd
    -0.46
    thargy
    -0.45
    Gam
    -0.45
    цездатний
    -0.45
     GenerationType
    -0.44
     Gam
    -0.44
    gop
    -0.43
    oprot
    -0.41
     BAM
    -0.41
    POSITIVE LOGITS
     nice
    1.48
    Nice
    1.13
    nice
    1.08
     Nice
    1.05
     wonderful
    0.87
     interesting
    0.86
     good
    0.79
     NICE
    0.76
     gratifying
    0.75
     lovely
    0.73
    Activations Density 0.206%

    No Known Activations