© 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. 24-GEMMASCOPE-RES-16K
    11. 5037
    Prev
    Next
    INDEX
    Explanations

    indicators of project progress and completion

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

    Indicates the completion or near completion of an action

    np_acts-logits-general · gemini-2.0-flash

    states of completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    saraba
    -0.69
    SequentialGroup
    -0.62
    GLI
    -0.60
     kasarigan
    -0.58
    '][]
    -0.57
    NewGuid
    -0.56
     niitä
    -0.55
     setuptools
    -0.55
    ANDUM
    -0.54
    Hochspringen
    -0.54
    POSITIVE LOGITS
     complete
    1.52
     finished
    1.36
     ready
    1.21
    complete
    1.20
     completed
    1.18
     done
    1.16
     COMPLETE
    1.07
     Complete
    1.06
    Complete
    1.04
     nearly
    0.99
    Activations Density 0.193%

    No Known Activations