© 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. 3208
    Prev
    Next
    INDEX
    Explanations

    elements of storytelling and engagement related to actions and choices

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

    gerund forms of action verbs (verbs ending in '-ing' that function as nouns or describe ongoing actions).

    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
    
    -0.55
     Wohnen
    -0.50
     otomatig
    -0.48
     Dazu
    -0.45
     épaules
    -0.45
    verifyException
    -0.43
    braucher
    -0.43
    Personendaten
    -0.42
    rizona
    -0.42
    getInstance
    -0.41
    POSITIVE LOGITS
    رشف
    0.55
     groceries
    0.46
     furs
    0.46
     trophies
    0.45
    extAlignment
    0.44
     passwords
    0.43
     refunds
    0.43
     pots
    0.42
     badges
    0.41
     cabs
    0.41
    Activations Density 0.828%

    No Known Activations