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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 39516
    Prev
    Next
    INDEX
    Explanations

    mathematical conditions and inequalities related to numerical relationships

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

    number followed by punctuation

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     TextAppearance
    -0.40
     Sound
    -0.36
     cancelled
    -0.36
     canceled
    -0.35
     Loop
    -0.35
     supported
    -0.34
     aided
    -0.34
     maximized
    -0.34
    __":
    -0.33
     Supported
    -0.33
    POSITIVE LOGITS
    Tikang
    0.63
    enumii
    0.58
    :✨
    0.54
     protoimpl
    0.52
    pecabe
    0.51
    verifyException
    0.50
     transfieras
    0.50
    StylePriority
    0.50
     cherchés
    0.49
    +:+
    0.49
    Activations Density 0.018%

    No Known Activations