© 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. 3785
    Prev
    Next
    INDEX
    Explanations

    expressions of insistence or persistence in opinions and actions

    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
    Kitchen
    -0.55
    amssymb
    -0.50
     kitchens
    -0.50
    ьа
    -0.49
    ayangkan
    -0.49
     Kitchens
    -0.47
    قاب
    -0.45
    PostConstruct
    -0.44
    CodeAnalysis
    -0.44
    quién
    -0.44
    POSITIVE LOGITS
     insist
    1.32
     insisted
    1.29
     insistence
    1.26
     insisting
    1.23
     insists
    1.20
     insiste
    1.05
     persist
    1.03
     persistence
    1.03
     insistent
    1.01
     persisted
    0.94
    Activations Density 0.553%

    No Known Activations