© 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. 0-GEMMASCOPE-RES-16K
    11. 3297
    Prev
    Next
    INDEX
    Explanations

    instances of the word "hat" along with variations in the surrounding content, suggesting a focus on specific notation or terms often used in mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     indígen
    -0.82
    AndEndTag
    -0.78
     فريبيس
    -0.77
    <unused43>
    -0.77
    <unused74>
    -0.77
    StoryboardSegue
    -0.77
     ſch
    -0.77
    <unused41>
    -0.77
     $_"
    -0.77
    <pad>
    -0.76
    POSITIVE LOGITS
     hat
    0.93
    hat
    0.79
     shot
    0.70
    Hat
    0.59
     Hat
    0.58
    HAT
    0.56
     haben
    0.53
     hats
    0.52
     Dar
    0.51
        
    0.49
    Activations Density 0.418%

    No Known Activations