© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 85230
    Prev
    Next
    INDEX
    Explanations

    representations of mathematical symbols, particularly those related to equations and formatting

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

    math labels and greek letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.96
     المعيارى
    -0.96
     betweenstory
    -0.94
     queſta
    -0.94
    tvguidetime
    -0.92
     AssemblyVersion
    -0.90
     estekak
    -0.89
    iffance
    -0.88
    adaptiveStyles
    -0.87
    mpagne
    -0.87
    POSITIVE LOGITS
     the
    0.56
    the
    0.39
    The
    0.39
    $\
    0.37
     $\
    0.36
    ,
    0.35
    \
    0.33
     it
    0.31
    $$\
    0.31
     \
    0.30
    Activations Density 0.041%

    No Known Activations