© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 1357
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases relating to product quality and design features

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

    Follows descriptive adjectives

    np_acts-logits-general · gemini-2.0-flash

    selling photographs, new project

    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
    apparently
    -0.69
     betweenstory
    -0.67
     jakieś
    -0.67
     нещо
    -0.65
     Apparently
    -0.62
     Sometime
    -0.62
     apparently
    -0.62
     hitherto
    -0.61
    Apparently
    -0.59
    RenderAtEndOf
    -0.58
    POSITIVE LOGITS
     youll
    0.65
    Featuring
    0.65
     featuring
    0.63
     convenient
    0.62
     Featuring
    0.61
     ideal
    0.60
    OOTDTY
    0.60
     durable
    0.60
     design
    0.59
     features
    0.59
    Activations Density 0.117%

    No Known Activations