© 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 EvalsExportsAPI 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. 15054
    Prev
    Next
    INDEX
    Explanations

    references to legal or regulatory processes regarding timeframes and events

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

    Word before/after "begins" or "timing"

    np_acts-logits-general · gemini-2.0-flash

    timing of events

    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
    اظ
    -0.47
    Multiply
    -0.46
    spół
    -0.46
     unarmed
    -0.46
    以上に
    -0.44
    ężczy
    -0.44
     saites
    -0.44
    百
    -0.43
    twimg
    -0.42
    offsetof
    -0.42
    POSITIVE LOGITS
     delayed
    1.24
     timing
    1.21
     earliest
    1.19
     Timing
    1.16
    delayed
    1.08
     ModelExpression
    1.08
     EARLY
    1.07
     Delayed
    1.06
     delay
    1.06
    Early
    1.05
    Activations Density 0.807%

    No Known Activations