© 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 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. 1319
    Prev
    Next
    INDEX
    Explanations

    instances of the word "collect" and its variations indicating actions related to gathering information or data

    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
     FontWeight
    -0.64
    cstring
    -0.63
     CURIAM
    -0.63
     Ord
    -0.63
     Farr
    -0.62
    aarrggbb
    -0.60
    ResponseEntity
    -0.58
    vantaged
    -0.57
    espan
    -0.57
     Gas
    -0.56
    POSITIVE LOGITS
    collect
    2.59
     Collect
    2.53
     collect
    2.52
     collected
    2.45
    Collect
    2.42
     collects
    2.40
     collecting
    2.39
     Collecting
    2.35
     COLLECT
    2.31
    Collecting
    2.26
    Activations Density 0.072%

    No Known Activations