© 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. 18-GEMMASCOPE-RES-16K
    11. 11122
    Prev
    Next
    INDEX
    Explanations

    quantitative metrics and measurements used in research studies

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

    Units of measurement or time

    np_acts-logits-general · gemini-2.0-flash

    in units of measure

    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
    '))
    -0.53
    brainly
    -0.50
    FRIDAY
    -0.49
    },[])
    -0.48
    WEDNESDAY
    -0.48
     Kombat
    -0.45
    TUESDAY
    -0.45
    ğından
    -0.44
    चना
    -0.43
    ')));
    -0.43
    POSITIVE LOGITS
     units
    1.05
     measured
    0.97
     inches
    0.96
     milli
    0.93
     dollars
    0.90
     cents
    0.86
    expressed
    0.86
    单位
    0.85
     miles
    0.85
     milligrams
    0.84
    Activations Density 0.731%

    No Known Activations