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. 1118
    Prev
    Next
    INDEX
    Explanations

    proper names and titles of individuals, particularly in military or formal contexts

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

    academic and professional titles

    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
    دانشنامهٔ
    -0.72
     AssemblyCulture
    -0.64
    scriptcase
    -0.56
    SourceChecksum
    -0.56
    InSection
    -0.53
    LookAnd
    -0.52
     كومونز
    -0.52
     OMITBAD
    -0.51
     препратки
    -0.50
     HttpNotFound
    -0.49
    POSITIVE LOGITS
     thermometer
    0.39
     scholar
    0.39
     Charities
    0.39
     master
    0.38
     professional
    0.36
     makinesi
    0.36
     Scholar
    0.36
     barrister
    0.35
     Scholarship
    0.35
     Thermometer
    0.34
    Activations Density 0.002%

    No Known Activations