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. 23-GEMMASCOPE-RES-131K
    6. 48
    Prev
    Next
    INDEX
    Explanations

    references to software releases and updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_131k/average_l0_101
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     recorded
    -0.40
     written
    -0.38
     family
    -0.33
     trip
    -0.33
     institutional
    -0.32
    Plot
    -0.32
    NamedQuery
    -0.32
     professional
    -0.31
     food
    -0.31
     bond
    -0.31
    POSITIVE LOGITS
    adget
    0.83
     surla
    0.80
     ब्रेकडाउन
    0.65
    IUrlHelper
    0.64
    pertino
    0.63
    hoeddwyd
    0.63
     hardware
    0.63
     tecnológica
    0.62
    قایناق‌لار
    0.62
     gadget
    0.61
    Activations Density 0.060%

    No Known Activations