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. 4-GEMMASCOPE-RES-16K
    6. 563
    Prev
    Next
    INDEX
    Explanations

    calls to action encouraging readers to check out content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DCP
    -0.61
    uxxxx
    -0.60
    Datuak
    -0.60
     Asked
    -0.58
    QMetaType
    -0.57
    isRequired
    -0.56
     digress
    -0.54
    Прави
    -0.54
     Bc
    -0.54
    рация
    -0.54
    POSITIVE LOGITS
     Checkout
    1.17
    Checkout
    1.11
     checkout
    1.04
    checkout
    0.80
     confira
    0.77
    DockStyle
    0.74
     Confira
    0.74
     vistazo
    0.68
    Explore
    0.63
    unggulan
    0.61
    Activations Density 0.111%

    No Known Activations