© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 11385
    Prev
    Next
    INDEX
    Explanations

    conditional clauses or conjunctions indicating relationships between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     either
    -0.41
    ambilan
    -0.41
     subsequent
    -0.40
     transmission
    -0.39
     Biele
    -0.39
     fjer
    -0.37
     aside
    -0.36
     blanches
    -0.35
     oignons
    -0.35
    ɵɵelementStart
    -0.35
    POSITIVE LOGITS
     że
    2.20
     hogy
    2.00
     dass
    1.92
     že
    1.72
     että
    1.69
     ότι
    1.59
     daß
    1.53
     rằng
    1.43
     iż
    1.33
    ว่า
    1.30
    Activations Density 0.041%

    No Known Activations