© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8904
    Prev
    Next
    INDEX
    Explanations

    structured data or code related to geometric shapes and drawings

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

    Shapes, especially after certain punctuation

    np_acts-logits-general · gemini-2.0-flash

    geometric shapes

    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
    Personendaten
    -0.55
     समीक्षाओं
    -0.53
    wicket
    -0.52
    rijfs
    -0.50
    onViewCreated
    -0.50
     gainera
    -0.49
    ProgressHUD
    -0.49
    enumii
    -0.48
     disambiguazione
    -0.47
     noten
    -0.47
    POSITIVE LOGITS
     circle
    1.11
     rectangle
    1.07
     rectangular
    1.06
    circle
    1.04
     circles
    1.01
     circular
    1.01
     rectangles
    0.96
     straight
    0.96
     Circle
    0.94
    Circle
    0.93
    Activations Density 0.652%

    No Known Activations