© 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. 2503
    Prev
    Next
    INDEX
    Explanations

    terms related to detection and monitoring in various contexts

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

    "detect" or "detecting"

    np_acts-logits-general · gemini-2.0-flash

    detecting specific conditions or subjects

    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
    migrationBuilder
    -0.81
    findpost
    -0.59
    +#+#
    -0.54
     Considered
    -0.53
    ải
    -0.50
    viesa
    -0.49
    zeczytaj
    -0.49
    considered
    -0.48
     sentito
    -0.48
    WriteAttribute
    -0.48
    POSITIVE LOGITS
     hidden
    0.95
     subtle
    0.85
     abnormalities
    0.83
     CreateTagHelper
    0.81
     signs
    0.80
    hidden
    0.80
     irregularities
    0.79
     suspicious
    0.76
     changes
    0.75
     presence
    0.75
    Activations Density 0.842%

    No Known Activations