© 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. 14285
    Prev
    Next
    INDEX
    Explanations

    determined effort and resilience in various contexts

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

    "hard" or its variations

    np_acts-logits-general · gemini-2.0-flash

    work hard

    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
     ComVisible
    -0.73
    IntoConstraints
    -0.67
    VersionUID
    -0.66
     незавершена
    -0.64
    sidemargin
    -0.63
    Gambas
    -0.63
    awtextra
    -0.61
    contentLoaded
    -0.59
     onAnimation
    -0.59
     الاطلاع
    -0.59
    POSITIVE LOGITS
     hard
    2.44
    hard
    1.95
     HARD
    1.87
     harder
    1.78
    HARD
    1.77
    Hard
    1.76
     Hard
    1.73
     hardest
    1.57
     Harder
    1.30
     hård
    1.24
    Activations Density 0.250%

    No Known Activations