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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 55551
    Prev
    Next
    INDEX
    Explanations

    elements related to video content and its attributes

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

    numerical sequences in URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     R
    -0.30
     H
    -0.30
     inside
    -0.29
     contra
    -0.29
     applied
    -0.28
     mid
    -0.28
     dé
    -0.28
     con
    -0.27
    一
    -0.27
     The
    -0.26
    POSITIVE LOGITS
    unsplash
    1.39
     disambiguazione
    1.02
    GEBURTSDATUM
    0.94
    MLLoader
    0.88
    +#+
    0.85
     autorytatywna
    0.82
     незавершена
    0.80
     للمعارف
    0.79
    AddTagHelper
    0.76
    ConstraintMaker
    0.75
    Activations Density 0.003%

    No Known Activations