© 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. 1410
    Prev
    Next
    INDEX
    Explanations

    dates and times

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

    month/day/year formats

    np_acts-logits-general · gemini-2.0-flash

    dates and preceding text

    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
    aarrggbb
    -0.54
     autorytatywna
    -0.53
    Rptr
    -0.53
    Biografia
    -0.49
     AssemblyCompany
    -0.45
    abestanden
    -0.44
    jsonwebtoken
    -0.44
    AxisAlignment
    -0.43
    woordig
    -0.43
     Races
    -0.43
    POSITIVE LOGITS
     preceding
    0.47
    Personendaten
    0.47
     previous
    0.47
     previo
    0.44
     vorher
    0.40
     previos
    0.40
    before
    0.40
    tagext
    0.39
    previous
    0.38
     Eng
    0.37
    Activations Density 0.504%

    No Known Activations