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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12370
    Prev
    Next
    INDEX
    Explanations

    references to cultural or communal identity, particularly relating to family and tradition

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

    after "ism"

    np_acts-logits-general · gemini-2.0-flash

    Marxist principles, proper authenticity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    ChildScrollView
    -0.67
    FieldBuilder
    -0.59
     ErrInvalid
    -0.50
    complexContent
    -0.49
     StatefulWidget
    -0.49
    exitRule
    -0.49
    FormTagHelper
    -0.48
    Parcelize
    -0.47
    ThroughAttribute
    -0.47
    AlterField
    -0.45
    POSITIVE LOGITS
    :✨
    0.46
    authentic
    0.38
     onore
    0.36
    Notae
    0.35
    honor
    0.35
     authentic
    0.35
    aronder
    0.34
     authenticity
    0.34
     zijne
    0.34
     honor
    0.34
    Activations Density 0.596%

    No Known Activations