© 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. 6788
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "see" and its variations

    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
    الإنجليزية
    -0.47
     linkovi
    -0.46
    enregistrement
    -0.44
     trouw
    -0.43
     behalten
    -0.42
    endregion
    -0.41
    amitié
    -0.41
     warunki
    -0.41
     Rosas
    -0.41
    consulté
    -0.41
    POSITIVE LOGITS
     seen
    0.83
     saw
    0.82
     Seen
    0.75
    saw
    0.74
    Seen
    0.72
    seen
    0.71
     heard
    0.70
     seeing
    0.67
     sees
    0.67
    Saw
    0.67
    Activations Density 0.307%

    No Known Activations