© 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. 22-GEMMASCOPE-RES-16K
    6. 14284
    Prev
    Next
    INDEX
    Explanations

    words related to possession or existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Comes before "serious," "abandoned," "a," or "reviewed"

    np_acts-logits-general · gemini-2.0-flash

    have/has

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CommonModule
    -0.59
     &___
    -0.56
    stateProvider
    -0.52
    omenclature
    -0.51
    CreateMap
    -0.51
     متعلقه
    -0.51
    memoized
    -0.49
    etur
    -0.48
    lysm
    -0.47
    ValueStyle
    -0.47
    POSITIVE LOGITS
    ScopeManager
    0.73
    RenderAtEndOf
    0.72
     {},
    
    0.68
     iNdEx
    0.63
     hitherto
    0.62
     cauſe
    0.62
     recourse
    0.58
    TypedDataSet
    0.57
     хватает
    0.56
     throughout
    0.56
    Activations Density 0.390%

    No Known Activations