© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 1791
    Prev
    Next
    INDEX
    Explanations

    phrases related to processes 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
     fallu
    -0.55
     tratado
    -0.54
     dataSnapshot
    -0.51
     skick
    -0.50
     changé
    -0.47
    drill
    -0.47
     camicia
    -0.46
    AuthGuard
    -0.46
    openConnection
    -0.45
     vives
    -0.45
    POSITIVE LOGITS
    tagHelperRunner
    0.72
     ProtoMessage
    0.71
    Jereo
    0.69
    verwijspagina
    0.69
    Искәрмәләр
    0.68
    WireFormatLite
    0.67
    InSection
    0.64
    SharedCtor
    0.60
    addCriterion
    0.60
    oa̍t
    0.57
    Activations Density 1.010%

    No Known Activations