© 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. 24-GEMMASCOPE-RES-16K
    11. 4712
    Prev
    Next
    INDEX
    Explanations

    themes related to political and territorial disputes

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

    preceding "ceased," "quite," "only," "been," "know," or "reference."

    np_acts-logits-general · gemini-2.0-flash

    negation and avoidance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.99
     lenker
    -0.95
     resourceCulture
    -0.89
    gameserver
    -0.85
    LookAnd
    -0.85
    EDEFAULT
    -0.81
    expandindo
    -0.81
    RectangleBorder
    -0.80
    DataAnnotations
    -0.80
     ddelweddau
    -0.79
    POSITIVE LOGITS
    retanto
    0.50
     either
    0.50
     Púb
    0.47
     infrequently
    0.47
     aught
    0.47
     finally
    0.46
     Akhir
    0.46
     except
    0.45
    mith
    0.45
     Enfin
    0.44
    Activations Density 0.559%

    No Known Activations