Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K__L0-22
    6. 128
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_22
    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
    #+#
    -0.57
    toLowerCase
    -0.55
    elux
    -0.50
    unched
    -0.50
    vosti
    -0.49
    volles
    -0.48
    UNCH
    -0.47
    inctive
    -0.47
    capit
    -0.46
    ◾
    -0.46
    POSITIVE LOGITS
     distance
    1.20
     distant
    1.19
     distances
    1.13
     distanced
    1.07
    distant
    1.07
     distante
    1.05
     élo
    1.04
     Distant
    1.02
     Distance
    1.02
     DISTANCE
    1.01
    Activations Density 0.103%

    No Known Activations