© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1700
    Prev
    Next
    INDEX
    Explanations

    the definite article "the" in various contexts

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

    "The" followed by a reason, subject, problem, etc

    np_acts-logits-general · gemini-2.0-flash

    The specific noun or adjective

    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
    tvguidetime
    -0.78
     wikipagina
    -0.71
    +#+#
    -0.70
    routeProvider
    -0.66
    Aiheesta
    -0.61
    RunAsync
    -0.61
    IUrlHelper
    -0.60
     policiales
    -0.59
    TargetException
    -0.58
     navideñas
    -0.57
    POSITIVE LOGITS
     only
    1.05
     reason
    0.92
     most
    0.87
     result
    0.81
     idea
    0.80
     entire
    0.79
    only
    0.79
     easiest
    0.78
     einzige
    0.77
     únicos
    0.73
    Activations Density 0.895%

    No Known Activations