© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 13257
    Prev
    Next
    INDEX
    Explanations

    references to handheld or manually operated objects and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 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
     Faure
    -0.43
    ally
    -0.43
     partecipare
    -0.43
    csp
    -0.42
    komna
    -0.42
    hancers
    -0.42
    jsp
    -0.41
    spotify
    -0.41
    UTERS
    -0.41
     combineReducers
    -0.41
    POSITIVE LOGITS
     hands
    1.29
     Hands
    1.27
     HAND
    1.25
     Hand
    1.20
     hand
    1.19
    Hand
    1.19
    Hands
    1.18
     HANDS
    1.17
    HAND
    1.15
    hands
    1.09
    Activations Density 0.137%

    No Known Activations