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. 1206
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables often used in equations and scientific notation

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

    imaginary unit in mathematical expressions

    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
     للمعارف
    -0.91
     purpoſe
    -0.73
    <unused28>
    -0.72
    <unused43>
    -0.72
    <unused8>
    -0.72
    <pad>
    -0.72
    <unused23>
    -0.72
    <unused47>
    -0.72
    <unused14>
    -0.72
    [@BOS@]
    -0.72
    POSITIVE LOGITS
    posedge
    0.36
    ly
    0.33
    i
    0.33
    I
    0.33
     i
    0.32
    j
    0.32
    true
    0.32
     virtual
    0.31
    y
    0.31
    (/
    0.31
    Activations Density 0.046%

    No Known Activations