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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 15770
    Prev
    Next
    INDEX
    Explanations

    features related to software capabilities and integrations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.99
     resourceCulture
    -0.96
    ValueStyle
    -0.90
    ьаж
    -0.86
    tvguidetime
    -0.85
    contentLoaded
    -0.84
    脚注の使い方
    -0.84
    verwijspagina
    -0.80
     <=",
    -0.79
    Portale
    -0.79
    POSITIVE LOGITS
     feature
    0.70
     functionality
    0.66
     features
    0.66
     user
    0.64
     mechanism
    0.63
     capability
    0.63
     allows
    0.62
     automatic
    0.61
     mode
    0.61
     capabilities
    0.59
    Activations Density 0.323%

    No Known Activations