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-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 5934
    Prev
    Next
    INDEX
    Explanations

    references to settings and configuration options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]<<"
    -0.95
     isolada
    -0.79
     otomatig
    -0.78
    unesse
    -0.75
     RemoteException
    -0.75
    umbered
    -0.74
    ֲ
    -0.74
    }}^{(
    -0.74
    csolódó
    -0.74
     hydroelectric
    -0.73
    POSITIVE LOGITS
    Settings
    1.45
     settings
    1.34
     Settings
    1.33
    settings
    1.28
     SETTINGS
    1.10
    SETTINGS
    1.06
    getSettings
    1.02
     SETTING
    0.90
     setting
    0.87
    AppSettings
    0.87
    Activations Density 0.087%

    No Known Activations