© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 15194
    Prev
    Next
    INDEX
    Explanations

    the word "taken" or variations of it, indicating actions related to custody or legal processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doInBackground
    -0.59
     crime
    -0.52
     N
    -0.46
     treo
    -0.46
     synes
    -0.46
     interactive
    -0.45
     Sh
    -0.45
    ngua
    -0.45
     U
    -0.45
    link
    -0.45
    POSITIVE LOGITS
     taken
    1.54
     obtained
    1.40
    obtained
    1.31
     Taken
    1.31
     collected
    1.30
    Taken
    1.23
     Obtained
    1.22
    taken
    1.15
    collected
    1.12
     TAKEN
    1.12
    Activations Density 0.185%

    No Known Activations