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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 12-GEMMASCOPE-RES-16K
    6. 9348
    Prev
    Next
    INDEX
    Explanations

    references to settings and preferences in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]<<"
    -0.88
     isolada
    -0.85
     AssemblyProduct
    -0.84
     RemoteException
    -0.82
     CreateTagHelper
    -0.81
     virtuales
    -0.79
    ExecuteReader
    -0.78
     beroep
    -0.77
     camiones
    -0.76
     оригіналу
    -0.76
    POSITIVE LOGITS
    Settings
    1.49
     settings
    1.37
     Settings
    1.37
    settings
    1.27
     SETTINGS
    1.15
    getSettings
    1.08
    SETTINGS
    1.06
     SETTING
    0.95
    AppSettings
    0.94
     setting
    0.94
    Activations Density 0.077%

    No Known Activations