© 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. 14862
    Prev
    Next
    INDEX
    Explanations

    references to cooperation and community involvement

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

    Attribution, especially with commas

    np_acts-logits-general · gemini-2.0-flash

    reporting verbs and attribution

    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
    });
    -0.52
    rubin
    -0.50
    aság
    -0.50
    lexikon
    -0.47
    Ợ
    -0.47
    phazard
    -0.47
    addCriterion
    -0.47
    ributions
    -0.46
    zma
    -0.46
    SBATCH
    -0.46
    POSITIVE LOGITS
     said
    1.87
     says
    1.82
    said
    1.66
    says
    1.58
     katanya
    1.54
    Says
    1.44
     Says
    1.40
     according
    1.40
    他说
    1.33
     dijo
    1.29
    Activations Density 0.635%

    No Known Activations