Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8615
    Prev
    Next
    INDEX
    Explanations

    phrases related to exclusive memberships and affiliations

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

    Elite groups or memberships

    np_acts-logits-general · gemini-2.0-flash

    elite and exclusive groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.81
    Билгалдахарш
    -0.74
    contentLoaded
    -0.73
    CppMethod
    -0.69
    elemField
    -0.68
    featureID
    -0.68
    Diweddarwch
    -0.67
     &___
    -0.65
    LayoutStyle
    -0.64
    AllAfrica
    -0.63
    POSITIVE LOGITS
     elite
    1.34
     exclusive
    1.26
     club
    1.22
    exclusive
    1.09
     eksklu
    1.09
     exklu
    1.06
    club
    1.06
     exclusivity
    1.05
     Club
    1.04
    elite
    1.01
    Activations Density 0.233%

    No Known Activations