© 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. 20-GEMMASCOPE-RES-16K
    11. 16363
    Prev
    Next
    INDEX
    Explanations

    elements related to data organization and retrieval processes

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

    German or Chinese language related

    np_acts-logits-general · gemini-2.0-flash

    most consecutive verbs

    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
    的多
    -0.52
     BoxDecoration
    -0.48
     Everywhere
    -0.47
    peen
    -0.47
     Forever
    -0.47
    ьаж
    -0.45
    的不同
    -0.43
    ektiv
    -0.43
    XtraEditors
    -0.42
    avro
    -0.42
    POSITIVE LOGITS
    +#+#
    0.90
     bezeichneter
    0.89
    __":
    0.74
    __':
    0.72
    "];
    0.69
     متعلقه
    0.68
    ulemon
    0.67
    ).”
    0.67
    )*/
    0.67
    uttavia
    0.66
    Activations Density 0.014%

    No Known Activations