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. 910
    Prev
    Next
    INDEX
    Explanations

    quantities and measurements related to chemical substances

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

    moles and chemical units

    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
    to
    -0.30
     (
    -0.27
     "
    -0.26
     “
    -0.26
     relative
    -0.25
    (*
    -0.25
    "
    -0.24
     v
    -0.24
    fillColor
    -0.24
    /~
    -0.24
    POSITIVE LOGITS
    MLLoader
    0.94
     ProtoMessage
    0.90
     EconPapers
    0.78
    ScopeManager
    0.73
    IContainer
    0.72
     CreateTagHelper
    0.70
     ModelExpression
    0.69
    ništvo
    0.68
    GOTREF
    0.67
    Rhestr
    0.67
    Activations Density 0.002%

    No Known Activations