© 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. 7796
    Prev
    Next
    INDEX
    Explanations

    discussions of support and resilience in challenging situations or relationships

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

    Overcoming adversity

    np_acts-logits-general · gemini-2.0-flash

    endure hardship and survive

    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
     Kens
    -0.49
    ahul
    -0.49
     Zeal
    -0.47
     Referential
    -0.47
     taus
    -0.47
    ayn
    -0.47
    prit
    -0.44
    Visit
    -0.44
    discre
    -0.44
     귀
    -0.44
    POSITIVE LOGITS
     survived
    1.46
     survive
    1.30
     survives
    1.20
    Surviving
    1.19
     surviving
    1.18
     weathering
    1.14
     weathered
    1.13
    survi
    1.12
     Survive
    1.12
     Survi
    1.11
    Activations Density 0.281%

    No Known Activations