© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 14446
    Prev
    Next
    INDEX
    Explanations

    mentions of specific organizations or initiatives aimed at poverty alleviation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    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
    -1.00
     ujednoznacz
    -0.83
     kasarigan
    -0.82
     AssemblyCompany
    -0.81
    Derbyniad
    -0.80
     esternos
    -0.80
     للاسماء
    -0.77
     Waray
    -0.73
     CreateTagHelper
    -0.73
    +#+
    -0.72
    POSITIVE LOGITS
     Wohnungen
    0.34
     Tübingen
    0.34
     Spitze
    0.32
     Ärz
    0.32
     alianza
    0.32
     Behörden
    0.31
     desean
    0.31
     Ärzte
    0.31
     Könige
    0.31
     Herzen
    0.31
    Activations Density 0.035%

    No Known Activations