© 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. 18-GEMMASCOPE-RES-16K
    6. 11201
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of people and political figures

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

    Follows a person's first name

    np_acts-logits-general · gemini-2.0-flash

    names with surnames

    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
     maîtres
    -0.52
    ůr
    -0.50
     riscal
    -0.50
     maîtrise
    -0.50
     precisione
    -0.49
    ecuzione
    -0.48
     nghề
    -0.47
     tombé
    -0.47
     producciones
    -0.47
     hoogte
    -0.47
    POSITIVE LOGITS
     дописавши
    0.76
    kháu
    0.72
    WebElementEntity
    0.72
     political
    0.69
    ">//
    0.65
    parsedMessage
    0.63
    RegressionTest
    0.63
     Biden
    0.62
    political
    0.61
    roupa
    0.61
    Activations Density 0.296%

    No Known Activations