© 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. 980
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the making or creation of something in a specific manner

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

    Preceding words of "such" or "make"

    np_acts-logits-general · gemini-2.0-flash

    make sure, such a way

    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
    can
    -0.55
    then
    -0.51
    but
    -0.51
    when
    -0.50
    Then
    -0.49
    rather
    -0.47
    what
    -0.46
    not
    -0.46
    was
    -0.45
    Thus
    -0.45
    POSITIVE LOGITS
    SizeF
    0.82
     autorytatywna
    0.80
     للاسماء
    0.78
    #+#
    0.77
    Transcripción
    0.77
    ]-->
    0.74
     resourceCulture
    0.73
    };*/
    0.72
    </tfoot>
    0.71
    )}</
    0.70
    Activations Density 0.198%

    No Known Activations