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. 1217
    Prev
    Next
    INDEX
    Explanations

    mentions of neural networks

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

    NN and nn variants

    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
    ']/
    -0.52
    tyle
    -0.51
    "]/
    -0.50
     BrowserModule
    -0.49
    IMPORTED
    -0.49
     المعيارى
    -0.47
    BrowserModule
    -0.45
    هما
    -0.45
    sstelle
    -0.44
     moeite
    -0.44
    POSITIVE LOGITS
     NN
    1.05
    NN
    1.04
    nn
    0.94
     nn
    0.93
    Nn
    0.78
    nnn
    0.77
    xnn
    0.77
     Annan
    0.73
     Nunn
    0.71
    enn
    0.68
    Activations Density 0.004%

    No Known Activations