© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2225
    Prev
    Next
    INDEX
    Explanations

    technical terms and error indicators in programming contexts

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

    Code snippets/programming-related text

    np_acts-logits-general · gemini-2.0-flash

    actions and objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.39
     Utilizamos
    -0.36
    IBOutlet
    -0.35
    UserScript
    -0.34
     CSO
    -0.34
    {}",
    -0.33
     celebrado
    -0.33
    jsonwebtoken
    -0.33
    معلومات
    -0.33
    {}".
    -0.33
    POSITIVE LOGITS
    Hozzáférés
    0.51
    SBATCH
    0.48
    もしろ
    0.47
     oprot
    0.47
     touch
    0.45
    findpost
    0.44
     TRANSFER
    0.44
     ivelany
    0.43
     دیکھیے
    0.43
    kuuta
    0.43
    Activations Density 1.093%

    No Known Activations