© 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. 16-GEMMASCOPE-RES-16K
    6. 9470
    Prev
    Next
    INDEX
    Explanations

    key locations and actions related to crime scenes and legal proceedings

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

    Preceding certain nouns/adjectives (a/an/the + noun/adjective)

    np_acts-logits-general · gemini-2.0-flash

    locations and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.78
     &___
    -0.60
     kaynağından
    -0.60
    msgSender
    -0.59
     referenties
    -0.55
     famí
    -0.54
    Garonne
    -0.54
     AssemblyCulture
    -0.51
    ledem
    -0.51
     intptr
    -0.50
    POSITIVE LOGITS
    Rptr
    0.71
     deserted
    0.64
    Clik
    0.63
     roadside
    0.63
    AnchorStyles
    0.62
     streets
    0.62
     viewDidLoad
    0.59
     ſtre
    0.59
     périph
    0.58
     EGL
    0.58
    Activations Density 0.445%

    No Known Activations