© 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. 13480
    Prev
    Next
    INDEX
    Explanations

    phrases expressing desires and wants

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

    Followed by "want"

    np_acts-logits-general · gemini-2.0-flash

    desire or preference

    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
    aarrggbb
    -0.62
    ScopeManager
    -0.57
    ue
    -0.52
     Lap
    -0.46
    Lap
    -0.46
    可
    -0.45
    发表于
    -0.45
    userManager
    -0.45
    )":
    -0.45
    ref
    -0.45
    POSITIVE LOGITS
     AssemblyCulture
    0.90
     purpoſe
    0.81
    ConstraintMaker
    0.80
     myſelf
    0.76
    ropractic
    0.74
     reaſon
    0.73
     beſt
    0.73
    Amicalement
    0.72
     greateſt
    0.70
    ffions
    0.69
    Activations Density 0.197%

    No Known Activations