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. 11-GEMMASCOPE-RES-16K
    6. 7170
    Prev
    Next
    INDEX
    Explanations

    different classes or types of icons and symbols

    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
    ագրություններ
    -1.07
     كومونز
    -0.96
    InputBorder
    -0.93
     فريبيس
    -0.92
     propOrder
    -0.91
     BoxFit
    -0.91
    DrawerToggle
    -0.90
    ſelf
    -0.89
     دیکھیے
    -0.87
    <?>>
    -0.87
    POSITIVE LOGITS
     Fa
    1.37
    fa
    1.28
     fa
    1.22
    Fa
    1.14
     Faulkner
    1.10
     FA
    1.07
    FA
    0.99
    faults
    0.81
     Faul
    0.78
     Faz
    0.77
    Activations Density 0.168%

    No Known Activations