© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10832
    Prev
    Next
    INDEX
    Explanations

    narratives related to personal commitment and sacrifice in situations involving significant investments or risks

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

    Sacrifice, resources, and energy

    np_acts-logits-general · gemini-2.0-flash

    sacrifice and expended resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    reportWebVitals
    -0.55
     surla
    -0.52
     veiks
    -0.50
     iklan
    -0.49
    amaño
    -0.48
    󠁴
    -0.48
     Majefty
    -0.47
     Lard
    -0.47
    scribers
    -0.47
     angekommen
    -0.47
    POSITIVE LOGITS
     resources
    0.48
    Sac
    0.46
     recursos
    0.43
     dedicated
    0.42
     sacrifice
    0.42
    resources
    0.41
     Sac
    0.39
     sacrificing
    0.39
     resource
    0.38
     sac
    0.38
    Activations Density 0.426%

    No Known Activations