© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1261
    Prev
    Next
    INDEX
    Explanations

    temporal references related to events and timelines

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

    Temporal location: "end", "start", or "middle"

    np_acts-logits-general · gemini-2.0-flash

    end or start of a period

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyProduct
    -0.69
    findpost
    -0.67
     utafitiHapana
    -0.66
    ftagPool
    -0.63
     المعيارى
    -0.61
     bieber
    -0.59
     بيها
    -0.56
     kiệm
    -0.56
     برانيه
    -0.55
     Italijani
    -0.55
    POSITIVE LOGITS
     mid
    1.17
     end
    1.09
     late
    1.08
     early
    1.05
     конце
    0.96
     середине
    0.88
     Ende
    0.88
     middle
    0.85
     mediados
    0.85
     metà
    0.84
    Activations Density 0.219%

    No Known Activations