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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 2610
    Prev
    Next
    INDEX
    Explanations

    specific references to objects or entities within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     asemenea
    -0.46
     rozwiąz
    -0.44
    Vidite
    -0.44
     komende
    -0.44
     zeker
    -0.42
     keber
    -0.40
    rungsseite
    -0.40
     betrekking
    -0.40
     onders
    -0.40
     rozwo
    -0.39
    POSITIVE LOGITS
    httphttps
    0.67
    IsMutable
    0.50
    cadilly
    0.48
     veranda
    0.47
     classroom
    0.47
     campus
    0.46
     neighbour
    0.46
     noisy
    0.46
     neighbourhood
    0.45
     supermarket
    0.45
    Activations Density 0.654%

    No Known Activations