Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 1232
    Prev
    Next
    INDEX
    Explanations

    references to function and object manipulation within programming code

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

    medical or programming contexts

    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
     MenuView
    -0.47
     megsz
    -0.43
    Predecesor
    -0.43
     groet
    -0.42
    )<<
    -0.42
    hears
    -0.42
    ]<<
    -0.41
     whatever
    -0.41
    noted
    -0.41
     aload
    -0.40
    POSITIVE LOGITS
     AssemblyCulture
    0.52
     ModelExpression
    0.52
     AssemblyCompany
    0.52
    出版年
    0.51
     defaultstate
    0.46
     useAppContext
    0.44
    istoitu
    0.41
     noDo
    0.41
    ガニック
    0.40
    Personensuche
    0.40
    Activations Density 0.009%

    No Known Activations