© 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. 20-GEMMASCOPE-RES-16K
    11. 10391
    Prev
    Next
    INDEX
    Explanations

    the presence of personal pronouns and indicative verbs related to existence or state

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

    Signaling something is finished or completed

    np_acts-logits-general · gemini-2.0-flash

    over, closed, finished, gone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mybatisplus
    -0.62
     Efq
    -0.61
     fallu
    -0.59
    createStatement
    -0.58
    URLException
    -0.58
    LikeLike
    -0.58
     iſt
    -0.57
     myſelf
    -0.56
     purpoſe
    -0.56
     }}"></
    -0.55
    POSITIVE LOGITS
     gone
    1.19
     done
    1.02
     ready
    0.90
     finished
    0.90
     dead
    0.88
    gone
    0.87
     DONE
    0.85
     GONE
    0.84
     Done
    0.83
    Done
    0.81
    Activations Density 0.321%

    No Known Activations