© 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. 15647
    Prev
    Next
    INDEX
    Explanations

    numerical data or values associated with statistics or performance metrics

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

    Code related to timers and constants

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal numbers and code timers

    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
     Oz
    -0.52
    Oz
    -0.49
     fler
    -0.47
     om
    -0.47
     global
    -0.46
    zola
    -0.46
    WebElementEntity
    -0.45
     ob
    -0.45
    oshin
    -0.44
     Olsen
    -0.44
    POSITIVE LOGITS
     Majefty
    0.84
     myſelf
    0.79
    MemoryWarning
    0.73
     themſelves
    0.73
     itſelf
    0.73
     ſever
    0.72
     Jefus
    0.71
     fevere
    0.70
     ſeveral
    0.69
     himſelf
    0.69
    Activations Density 0.398%

    No Known Activations