© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 8534
    Prev
    Next
    INDEX
    Explanations

    phrases related to functionality and user capabilities in software applications

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

    modal verbs and constructions expressing ability or possibility (especially "can," "could," "would," and "to").

    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
    skjaer
    -0.52
     propOrder
    -0.49
    はじめに
    -0.46
    帖最后由
    -0.44
     Infór
    -0.44
    ChildScrollView
    -0.43
    Jeografia
    -0.42
     AppCompatTheme
    -0.42
     firebaseConfig
    -0.42
     initComponents
    -0.42
    POSITIVE LOGITS
     easily
    0.84
    easily
    0.75
     customize
    0.67
     Easily
    0.65
     manipulate
    0.63
     управ
    0.62
     selectively
    0.62
     fácilmente
    0.61
     specify
    0.60
    Easily
    0.60
    Activations Density 0.635%

    No Known Activations