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. 862
    Prev
    Next
    INDEX
    Explanations

    names of individuals, especially family ties or relationships

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

    surname followed by comma

    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
     hap
    -0.39
     glut
    -0.38
    StackNavigator
    -0.37
     abi
    -0.36
     Cag
    -0.35
     py
    -0.35
    EndGlobalSection
    -0.35
     مُعرِّف
    -0.34
     relu
    -0.34
    tableCell
    -0.33
    POSITIVE LOGITS
    WebElementEntity
    0.65
    DockStyle
    0.55
    CloseOperation
    0.50
     AssemblyVersion
    0.50
     accompagn
    0.48
    ніципа
    0.47
    Personendaten
    0.46
    Демографія
    0.46
    UnusedPrivate
    0.46
     ivelany
    0.45
    Activations Density 0.000%

    No Known Activations