© 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. 15049
    Prev
    Next
    INDEX
    Explanations

    elements related to graphical structures and properties in mathematical contexts

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

    "above", "left", or "right"

    np_acts-logits-general · gemini-2.0-flash

    bend left or right

    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
     doubtnut
    -1.61
     itſelf
    -1.58
     myſelf
    -1.50
     pleaſure
    -1.38
    ſelf
    -1.37
     poffible
    -1.36
     Diſ
    -1.36
     Reſ
    -1.34
     photolibrary
    -1.33
     ſeveral
    -1.33
    POSITIVE LOGITS
     I
    0.99
     
    0.97
     y
    0.97
     A
    0.91
     i
    0.89
     van
    0.89
     Y
    0.89
     a
    0.88
     in
    0.87
     et
    0.86
    Activations Density 1.049%

    No Known Activations