© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 15680
    Prev
    Next
    INDEX
    Explanations

    phrases indicating cause and effect relationships

    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
     rangs
    -0.42
    ミング
    -0.42
    AxisAlignment
    -0.40
    ULAR
    -0.38
    coroutines
    -0.37
     worthwhile
    -0.37
    ďte
    -0.36
     Tagged
    -0.36
     Chriftian
    -0.35
     ozna
    -0.35
    POSITIVE LOGITS
    GEBURTSDATUM
    0.87
    ">//
    0.84
    homonymie
    0.82
     Мексичка
    0.82
     ويكيميديا
    0.79
    oredCriteria
    0.78
    RegistryLite
    0.77
    ArrowToggle
    0.77
     تضيفلها
    0.75
    wußt
    0.75
    Activations Density 1.158%

    No Known Activations