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. 10-GEMMASCOPE-RES-16K
    6. 15741
    Prev
    Next
    INDEX
    Explanations

    discourses related to authority and its implications in various contexts

    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
    r
    -0.50
     commerci
    -0.50
    encodeWith
    -0.47
    h
    -0.46
    /*
    -0.45
    📺
    -0.45
     stesso
    -0.44
    b
    -0.43
    l
    -0.43
    bo
    -0.43
    POSITIVE LOGITS
     AssemblyCulture
    0.84
    ChildScrollView
    0.83
     MainAxisSize
    0.81
    ValueStyle
    0.80
     defaultstate
    0.79
     NUKAT
    0.79
    Дереккөздер
    0.76
     gynhyrchwyd
    0.75
    ----</
    0.73
    matchCondition
    0.73
    Activations Density 0.892%

    No Known Activations