© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4411
    Prev
    Next
    INDEX
    Explanations

    terms and symbols related to mathematical expressions and notation

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

    LaTeX tilde (~) and hat (^) symbols

    np_acts-logits-general · gemini-2.0-flash

    $\tilde{}$ symbol transformations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.81
     ſans
    -0.75
     zwiſchen
    -0.75
    [@BOS@]
    -0.73
    <unused47>
    -0.73
    <pad>
    -0.73
    <unused41>
    -0.73
    <unused74>
    -0.73
    <unused8>
    -0.73
    <unused14>
    -0.73
    POSITIVE LOGITS
     version
    0.41
    版
    0.39
     versions
    0.34
     versión
    0.34
     NSCoder
    0.31
    ActionCreators
    0.31
    Everything
    0.28
    版的
    0.27
    version
    0.27
    ‌شده
    0.27
    Activations Density 1.279%

    No Known Activations