© 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. 3-GEMMASCOPE-RES-16K
    6. 13095
    Prev
    Next
    INDEX
    Explanations

    the term "worldwide" to denote global scope or reach

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.71
     things
    -0.65
     თ
    -0.60
    al
    -0.60
    IntoConstraints
    -0.60
     beans
    -0.60
    ={`/
    -0.59
    m
    -0.59
    makeText
    -0.59
    tagext
    -0.58
    POSITIVE LOGITS
     worldwide
    2.58
    Worldwide
    2.52
     Worldwide
    2.48
    worldwide
    2.46
     nationwide
    2.19
     Nationwide
    1.84
     weltweit
    1.60
     statewide
    1.52
     globally
    1.40
     Globally
    1.38
    Activations Density 0.050%

    No Known Activations