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

    Neuronpedia

    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. 22-GEMMASCOPE-RES-16K
    11. 8596
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to angles and their effects in physics or geometry, especially involving rays and zenith

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

    Mathematical angles

    np_acts-logits-general · gemini-2.0-flash

    geometric angles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Filmografie
    -0.64
    Vidite
    -0.59
    новниш
    -0.57
    localctx
    -0.54
    ocyto
    -0.53
     memu
    -0.52
     getItemId
    -0.51
    aville
    -0.50
     ujednoznacz
    -0.50
     Pristupljeno
    -0.50
    POSITIVE LOGITS
     angle
    2.03
     angles
    1.83
     Angle
    1.78
     ANGLE
    1.67
    angle
    1.65
    Angle
    1.65
     Angles
    1.48
    ANGLE
    1.37
    angles
    1.35
     ángulo
    1.34
    Activations Density 0.720%

    No Known Activations