© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10631
    Prev
    Next
    INDEX
    Explanations

    technical jargon related to medical or biological contexts

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

    or characters often followed by punctuation

    np_acts-logits-general · gemini-2.0-flash

    pyrazinamidase, dipropylamine, pyrazinoic

    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
    TagMode
    -1.20
    ArgsConstructor
    -1.03
     Paglinawan
    -1.02
    GraphicsUnit
    -0.99
    帖最后由
    -0.97
     AssemblyCompany
    -0.92
     ***!
    -0.90
     <<<<<<<<<<<<<<
    -0.90
    GEBURTSDATUM
    -0.88
     Efq
    -0.88
    POSITIVE LOGITS
     sub
    0.45
    </h2>
    0.44
     Nach
    0.43
     Flo
    0.42
    醐
    0.42
    tedt
    0.41
     T
    0.41
    isbury
    0.40
     AS
    0.40
     ant
    0.40
    Activations Density 0.975%

    No Known Activations