© 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. 16177
    Prev
    Next
    INDEX
    Explanations

    verbs indicating movement or change of state

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

    the phrase "went to" or similar constructions describing movement or travel to a specific location.

    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
     voorkomen
    -0.33
    brigens
    -0.32
    Written
    -0.32
     recovers
    -0.32
     Vorbe
    -0.30
    förs
    -0.30
     Written
    -0.30
    Hot
    -0.30
     Hot
    -0.30
     الفريق
    -0.29
    POSITIVE LOGITS
     AssemblyCulture
    0.62
     propOrder
    0.60
    NameInMap
    0.60
     ModelExpression
    0.60
    expandindo
    0.58
     kasarigan
    0.57
    ftagPool
    0.56
    chränk
    0.56
    BeginInit
    0.55
    bootstrapcdn
    0.53
    Activations Density 0.129%

    No Known Activations