© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15661
    Prev
    Next
    INDEX
    Explanations

    abilities and skills that involve movement, teleportation, and transformations in characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    -0.55
     يتيمه
    -0.48
     réfugi
    -0.47
    Билгалдахарш
    -0.46
    MemoryWarning
    -0.45
     Viitattu
    -0.44
    Становништво
    -0.44
    ļas
    -0.43
    middels
    -0.43
    fören
    -0.42
    POSITIVE LOGITS
    IUrlHelper
    0.46
     instantaneously
    0.45
     teleport
    0.44
     magically
    0.43
     disambiguazione
    0.43
    клопе
    0.42
    makeText
    0.41
    InputTagHelper
    0.41
     instantly
    0.40
    presto
    0.39
    Activations Density 0.141%

    No Known Activations