© 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. 16321
    Prev
    Next
    INDEX
    Explanations

    terms related to community support and development programs

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

    after certain nouns

    np_acts-logits-general · gemini-2.0-flash

    outcomes of financial and administrative processes

    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
    adaptiveStyles
    -0.70
     تانيه
    -0.69
     متعلقه
    -0.66
    BufferException
    -0.60
    ViewImports
    -0.60
     corrom
    -0.60
    kloped
    -0.59
    ]));
    -0.59
     célèbres
    -0.58
     mío
    -0.58
    POSITIVE LOGITS
     outcome
    0.60
     output
    0.59
    \@
    0.59
     credentials
    0.58
     scenario
    0.57
     status
    0.57
     expression
    0.56
     activity
    0.56
     arrangement
    0.56
     structure
    0.56
    Activations Density 1.687%

    No Known Activations