© 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. 16-GEMMASCOPE-RES-16K
    11. 8460
    Prev
    Next
    INDEX
    Explanations

    phrases associated with the action of picking something up

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

    "pick" and its variations

    np_acts-logits-general · gemini-2.0-flash

    pick up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.80
    rativa
    -0.79
     CURIAM
    -0.79
     defaultstate
    -0.78
    enderror
    -0.76
    LookAnd
    -0.75
    Personendaten
    -0.74
    */].
    -0.71
    AFA
    -0.71
    MigrationBuilder
    -0.71
    POSITIVE LOGITS
     pick
    1.52
     PICK
    1.43
    Pick
    1.42
    pick
    1.39
     Pick
    1.37
     picked
    1.36
    Picking
    1.33
     picking
    1.33
     Picking
    1.32
    PICK
    1.28
    Activations Density 0.032%

    No Known Activations