© 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. 16-GEMMASCOPE-RES-16K
    6. 13450
    Prev
    Next
    INDEX
    Explanations

    words related to thickness and thinness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+
    -0.75
     NavController
    -0.74
    \{\\
    -0.71
    ロウィン
    -0.69
    MemoryWarning
    -0.69
     müſſen
    -0.68
    BASEPATH
    -0.66
    нгред
    -0.66
    حياته
    -0.65
    MLLoader
    -0.65
    POSITIVE LOGITS
     thick
    0.98
    Thickness
    0.91
     Thick
    0.90
    Thick
    0.85
     Thin
    0.85
     thicker
    0.85
     thin
    0.84
    thick
    0.83
     thickness
    0.81
    Thin
    0.77
    Activations Density 0.075%

    No Known Activations