© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 14118
    Prev
    Next
    INDEX
    Explanations

    references to combinations or blends of various elements

    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
    Dermott
    -0.61
     Ebert
    -0.58
    argin
    -0.56
    出版年
    -0.56
    \{\\
    -0.56
     McMahon
    -0.56
    httphttps
    -0.56
     MainAxisSize
    -0.55
     AssemblyTitle
    -0.54
    urlopen
    -0.54
    POSITIVE LOGITS
     mix
    1.78
     mixture
    1.54
     mixed
    1.52
     MIX
    1.51
     Mix
    1.47
     mixes
    1.46
     mixtures
    1.45
     mezcla
    1.41
     mixing
    1.41
    Mix
    1.41
    Activations Density 0.314%

    No Known Activations