© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 124690
    Prev
    Next
    INDEX
    Explanations

    numerical representations or counts related to statistics and records

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

    birth dates

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     majeurs
    -0.33
    absch
    -0.33
     назначения
    -0.31
     intptr
    -0.31
     verwij
    -0.31
    providedIn
    -0.30
     selanjutnya
    -0.30
    .
    -0.30
     woorden
    -0.28
    äher
    -0.28
    POSITIVE LOGITS
    GEBURTSDATUM
    1.02
    səhifə
    0.80
     nakalista
    0.71
    Autoritní
    0.70
    iſche
    0.70
    ViewImports
    0.70
     dieſem
    0.69
     dieſes
    0.69
     ſeinen
    0.68
    iſchen
    0.67
    Activations Density 0.005%

    No Known Activations