© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 666
    Prev
    Next
    INDEX
    Explanations

    references to changes and their impacts, particularly in a financial or evaluative context

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

    change and difference

    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
     kasarigan
    -0.63
    MLLoader
    -0.63
     <<<<<<<<<<<<<<
    -0.59
     snippetHide
    -0.58
    webElementXpaths
    -0.58
     ivelany
    -0.57
    Хьажоргаш
    -0.55
    httphttps
    -0.55
    MessageOf
    -0.53
    ⓧ
    -0.52
    POSITIVE LOGITS
     differently
    0.59
     different
    0.56
     changed
    0.50
     attitudes
    0.50
     differ
    0.48
    different
    0.48
     anders
    0.48
     opinions
    0.46
     Different
    0.45
     diferente
    0.45
    Activations Density 0.091%

    No Known Activations