© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14076
    Prev
    Next
    INDEX
    Explanations

    references to film-viewing experiences

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

    after verbs in reviews or narratives

    np_acts-logits-general · gemini-2.0-flash

    recalling past events

    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
    RectangleBorder
    -0.29
    shadowOpacity
    -0.28
    künfte
    -0.28
     erreichbar
    -0.27
     Champagne
    -0.27
     Konzept
    -0.26
     anti
    -0.26
     LoginComponent
    -0.26
     maan
    -0.26
     lī
    -0.25
    POSITIVE LOGITS
     autorytatywna
    0.66
    AutoScaleMode
    0.63
    ########.
    0.60
    recently
    0.60
    XmlAccessType
    0.59
     recently
    0.59
     kemarin
    0.58
    wiliwch
    0.55
    SequentialGroup
    0.55
     toured
    0.54
    Activations Density 0.105%

    No Known Activations