© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14415
    Prev
    Next
    INDEX
    Explanations

    geometric shapes and their properties

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

    Triangles or triangular shapes

    np_acts-logits-general · gemini-2.0-flash

    triangles and crosses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ウター
    -0.41
    Життєпис
    -0.36
    NavController
    -0.33
    ]")]
    -0.32
    cierge
    -0.32
     moder
    -0.31
    ствии
    -0.31
     NavController
    -0.30
    bietern
    -0.30
     massa
    -0.29
    POSITIVE LOGITS
    QUADS
    0.72
     rectangle
    0.71
     Rectangle
    0.69
     shaped
    0.69
     triangle
    0.69
    shaped
    0.68
     triangular
    0.67
     HasFactory
    0.66
    rectangle
    0.64
    ValueStyle
    0.63
    Activations Density 0.622%

    No Known Activations