© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2612
    Prev
    Next
    INDEX
    Explanations

    discussions of personal resilience in challenging situations

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

    language expressing volunteerism, community effort, and people doing work without expecting rewards.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    language highlighting selfless courage, perseverance, and hard work for others, especially under danger or hardship.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    expressions of admiration or respect for people overcoming challenges or showing courage.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     gotcha
    -0.33
     برانيه
    -0.33
     starters
    -0.33
     commerces
    -0.33
     interro
    -0.32
    有所
    -0.31
     apres
    -0.30
     Penna
    -0.30
    MethodImpl
    -0.29
     interess
    -0.29
    POSITIVE LOGITS
    Ӕ
    0.68
     bravely
    0.56
     risking
    0.56
     brave
    0.53
     courageous
    0.51
     resourceCulture
    0.51
     courage
    0.50
     sacrifices
    0.50
     bravery
    0.50
     soportar
    0.49
    Activations Density 0.142%

    No Known Activations