Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 1032
    Prev
    Next
    INDEX
    Explanations

    symbols and operators used in mathematical contexts

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

    mathematical and programming symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.51
     ExecuteAsync
    -0.49
    ंदीखरीदारी
    -0.45
     pinulongan
    -0.41
     laajenta
    -0.40
     transfieras
    -0.40
    Kariera
    -0.40
    AutoScaleMode
    -0.40
    ItemBackground
    -0.39
     MyBatis
    -0.38
    POSITIVE LOGITS
     filtered
    0.43
     images
    0.43
     recorded
    0.41
     OrderedDict
    0.40
     obtained
    0.39
     edited
    0.39
     wigs
    0.39
     datasets
    0.39
     counterparts
    0.39
     compared
    0.38
    Activations Density 0.003%

    No Known Activations