Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15627
    Prev
    Next
    INDEX
    Explanations

    references to organizational missions and values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    الإنجليزية
    -0.56
    Personensuche
    -0.56
     للمعارف
    -0.52
    MethodManager
    -0.49
     ब्रेकडाउन
    -0.49
     ligiloj
    -0.49
    Carriera
    -0.48
    SerializedSize
    -0.47
     unknownFields
    -0.46
    Демографія
    -0.46
    POSITIVE LOGITS
     mission
    2.58
     Mission
    2.17
     MISSION
    2.05
    Mission
    2.03
     misión
    1.99
    mission
    1.98
     missão
    1.89
     missions
    1.80
     missione
    1.73
    MISSION
    1.66
    Activations Density 0.169%

    No Known Activations