© 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. 13464
    Prev
    Next
    INDEX
    Explanations

    variables, operators, and mathematical expressions in code or data analysis contexts

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

    Characters before numbers in chemical formulas

    np_acts-logits-general · gemini-2.0-flash

    range symbols followed by digits

    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
     and
    -0.29
     over
    -0.28
     
    -0.28
    a
    -0.27
     a
    -0.27
     ber
    -0.27
     çıktı
    -0.25
     or
    -0.25
     c
    -0.25
     r
    -0.24
    POSITIVE LOGITS
    MigrationBuilder
    1.15
     Infórmanos
    1.11
     CreateTagHelper
    1.08
    ########.
    1.06
    ConstraintMaker
    0.96
     صوتيه
    0.94
    OGND
    0.92
    <unused79>
    0.91
    [@BOS@]
    0.90
    :✨
    0.90
    Activations Density 1.358%

    No Known Activations