© 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. 16-GEMMASCOPE-RES-16K
    11. 6874
    Prev
    Next
    INDEX
    Explanations

    mathematical relationships and coefficients in geometric contexts

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

    Geometry (angles and triangles)

    np_acts-logits-general · gemini-2.0-flash

    angles and triangles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.69
    دانشنامهٔ
    -0.66
     EconPapers
    -0.64
    ProgressHUD
    -0.63
    afficheront
    -0.60
    kijken
    -0.59
     referenties
    -0.59
    SourceChecksum
    -0.58
     ErrIntOverflow
    -0.58
    셨
    -0.57
    POSITIVE LOGITS
    StoryboardSegue
    0.67
     triangle
    0.52
     triangles
    0.50
     AIA
    0.50
    lader
    0.49
     Perimeter
    0.48
     Draws
    0.48
     Drawings
    0.48
    닮
    0.48
     SIMBAD
    0.47
    Activations Density 0.441%

    No Known Activations