© 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. 198
    Prev
    Next
    INDEX
    Explanations

    phrases related to timelines and predictions regarding events

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

    approximate time

    np_acts-logits-general · gemini-2.0-flash

    sometime, early, late, or expected

    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
    WebVitals
    -0.68
    ftagPool
    -0.56
    jaros
    -0.55
    )++;
    -0.53
    примеча
    -0.53
     HasFactory
    -0.53
    Diweddarwch
    -0.51
     enx
    -0.51
    áles
    -0.50
     فريبيس
    -0.50
    POSITIVE LOGITS
     sometime
    1.46
     Sometime
    1.33
     early
    1.32
     late
    1.30
    early
    1.14
     mid
    1.14
     earliest
    1.11
     somewhere
    1.11
    late
    1.05
     probably
    1.03
    Activations Density 0.305%

    No Known Activations