© 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. 15580
    Prev
    Next
    INDEX
    Explanations

    key attributes and significant descriptors related to scientific models and their evaluation

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

    ending in "ly" or similar suffixes

    np_acts-logits-general · gemini-2.0-flash

    describing specific instances or states

    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
     ModelExpression
    -0.78
     almeno
    -0.71
     enfin
    -0.71
     stesse
    -0.71
     addirittura
    -0.69
     AssemblyTitle
    -0.69
     lezioni
    -0.69
     définiti
    -0.68
     écout
    -0.67
     partea
    -0.66
    POSITIVE LOGITS
    LY
    0.84
    eſt
    0.80
     $_"
    0.78
    leſs
    0.74
    ly
    0.73
    ENED
    0.72
     high
    0.70
    $$
    0.70
    Iy
    0.69
    적인
    0.69
    Activations Density 1.668%

    No Known Activations