© 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. 31-GEMMASCOPE-RES-16K
    11. 3270
    Prev
    Next
    INDEX
    Explanations

    mentions of doors and their operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    doors and door-related actions (opening, closing, or being in states like open/closed).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.58
     فريبيس
    -0.52
    Revenir
    -0.51
    Personendaten
    -0.50
    cshtml
    -0.48
    Становништво
    -0.46
    Sucesor
    -0.46
     TextInputType
    -0.46
    </thead>
    -0.45
    IUrlHelper
    -0.45
    POSITIVE LOGITS
     closed
    1.86
     opened
    1.76
     closing
    1.74
     opening
    1.72
     closure
    1.61
     closes
    1.57
     opens
    1.52
     Closed
    1.52
    Opening
    1.48
     Opening
    1.48
    Activations Density 0.409%

    No Known Activations