© 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-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 14830
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or tasks being performed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     uscire
    -0.64
     betrekking
    -0.63
     déplacements
    -0.57
     goes
    -0.57
    go
    -0.56
     parvenir
    -0.55
     Lleg
    -0.54
     moves
    -0.54
     NDEBUG
    -0.54
    move
    -0.54
    POSITIVE LOGITS
    extAlignment
    0.72
     discuss
    0.69
     see
    0.66
    ViewFeatures
    0.65
     greet
    0.64
     check
    0.63
     inspect
    0.63
     HasFactory
    0.63
     join
    0.59
    %)$
    0.59
    Activations Density 0.275%

    No Known Activations