© 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. 15334
    Prev
    Next
    INDEX
    Explanations

    terms related to isolation or isoform identification in scientific contexts

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

    "Iso" followed by a hyphen or other characters

    np_acts-logits-general · gemini-2.0-flash

    "iso-" prefix

    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
    клопе
    -0.80
     referenties
    -0.73
    </tfoot>
    -0.69
    IntoConstraints
    -0.69
    Statistiche
    -0.66
    cyd
    -0.65
    minecraftforge
    -0.65
    cloudf
    -0.65
    vább
    -0.63
     ComVisible
    -0.63
    POSITIVE LOGITS
     setIs
    0.66
    Anybody
    0.46
    جستارهای
    0.44
     isu
    0.43
    ías
    0.42
     jaundice
    0.42
    VIRGO
    0.42
     pamoja
    0.41
     još
    0.41
    Jau
    0.41
    Activations Density 0.125%

    No Known Activations