© 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. 7925
    Prev
    Next
    INDEX
    Explanations

    sensory descriptions related to light and warmth

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

    Things that emanate or are emitted

    np_acts-logits-general · gemini-2.0-flash

    sensory phenomena

    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
     учета
    -0.62
    lore
    -0.50
     thumb
    -0.49
     appended
    -0.48
    müş
    -0.48
    Sunny
    -0.47
     repose
    -0.47
     Sun
    -0.47
     orejas
    -0.47
    stery
    -0.46
    POSITIVE LOGITS
     emanating
    0.75
     generated
    0.71
    aarrggbb
    0.68
    DockStyle
    0.67
     coming
    0.67
     emitted
    0.63
     AssemblyCulture
    0.63
    IsContent
    0.63
    הערות
    0.63
    ChildScrollView
    0.62
    Activations Density 0.551%

    No Known Activations