© 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. 15418
    Prev
    Next
    INDEX
    Explanations

    SQL query terms and code structure related to service management

    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
    Ӕ
    -0.73
     esternos
    -0.73
    ロウィン
    -0.72
     виправивши
    -0.72
    síða
    -0.65
     HasFactory
    -0.62
    -------
    -0.61
    niſſe
    -0.60
    хьтан
    -0.60
     Normdatei
    -0.59
    POSITIVE LOGITS
     Grüsse
    0.43
    faßt
    0.32
    énario
    0.30
     Sobald
    0.28
     meliputi
    0.28
    wszy
    0.27
    pieler
    0.27
     školy
    0.26
     dilihat
    0.26
     biografias
    0.25
    Activations Density 0.291%

    No Known Activations