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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 7916
    Prev
    Next
    INDEX
    Explanations

    introductory elements or context for scientific discussions

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

    preceding "wide" (world, nation)

    np_acts-logits-general · gemini-2.0-flash

    scope of operation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.93
    ViewImports
    -0.62
     Overall
    -0.62
     statewide
    -0.61
    AccessorTable
    -0.60
    السكان
    -0.58
     المعيارى
    -0.58
    Einzelnachweise
    -0.56
    全局
    -0.56
    ReusableCell
    -0.56
    POSITIVE LOGITS
     autorytatywna
    0.68
     including
    0.66
    including
    0.59
     hinweg
    0.55
     hindurch
    0.55
    SizeF
    0.53
     democracies
    0.52
     oceans
    0.52
     včetně
    0.52
     termasuk
    0.50
    Activations Density 0.163%

    No Known Activations