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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 16229
    Prev
    Next
    INDEX
    Explanations

    references to legal and investigative terminology

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

    after specific nouns (team, children, agents, parties, countries)

    np_acts-logits-general · gemini-2.0-flash

    groups of people or entities

    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
    .
    -0.65
     go
    -0.59
    ).
    -0.57
    !
    -0.56
     
    -0.56
    .
    -0.56
     goes
    -0.54
    ?
    -0.53
     mình
    -0.52
    ].
    -0.52
    POSITIVE LOGITS
     whoſe
    1.25
     myſelf
    1.11
     pleaſure
    1.04
     reaſon
    1.01
     whofe
    0.99
     themſelves
    0.95
     ſeveral
    0.94
    InjectAttribute
    0.94
    ViewImports
    0.94
     purpoſe
    0.92
    Activations Density 0.988%

    No Known Activations