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. 911
    Prev
    Next
    INDEX
    Explanations

    method calls for searching or querying within data structures

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

    string searching functions

    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
     betweenstory
    -0.61
     elif
    -0.57
     CGSize
    -0.55
    outState
    -0.49
    PhysRevD
    -0.47
     UIC
    -0.46
     queſta
    -0.46
    OrEmpty
    -0.46
    CRIP
    -0.46
     ICollection
    -0.46
    POSITIVE LOGITS
    indexOf
    1.09
    lastIndexOf
    0.85
    IndexOf
    0.68
    getColumnIndex
    0.65
     indexOf
    0.60
    strpos
    0.57
    findIndex
    0.52
    FieldDescriptor
    0.51
     مرئيه
    0.46
     utafitiHapana
    0.45
    Activations Density 0.004%

    No Known Activations