© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3879
    Prev
    Next
    INDEX
    Explanations

    queries and expressions related to finding solutions or determining methods in coding and data handling

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

    "Is there" questions

    np_acts-logits-general · gemini-2.0-flash

    is there a way

    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
    rungsseite
    -0.78
    +#+
    -0.66
    Personensuche
    -0.60
     ujednoznacz
    -0.59
    WebElementEntity
    -0.58
    VIAF
    -0.56
     NSCoder
    -0.56
     '\\;'
    -0.55
     ſondern
    -0.55
     للمعارف
    -0.54
    POSITIVE LOGITS
     pros
    0.33
    astanza
    0.31
     secrets
    0.30
    できるだけ
    0.30
     alguma
    0.30
     possible
    0.29
     shortest
    0.27
     nogen
    0.27
     secretos
    0.27
     best
    0.27
    Activations Density 0.532%

    No Known Activations