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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 1349
    Prev
    Next
    INDEX
    Explanations

    sections of text that contain data or statistics

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

    Follows "Q:" or a country name

    np_acts-logits-general · gemini-2.0-flash

    technical terms and proper nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ausgleich
    -0.54
     textStatus
    -0.53
     domestiques
    -0.52
     exportación
    -0.52
    <h1>
    -0.50
    VersionUID
    -0.50
    marvin
    -0.49
     blé
    -0.49
     médicaux
    -0.49
     anyway
    -0.48
    POSITIVE LOGITS
    :✨
    1.11
    MigrationBuilder
    0.76
     الرياضيه
    0.74
    Kariera
    0.65
     Roskov
    0.65
    Personendaten
    0.65
    EndGlobalSection
    0.64
    RegistryLite
    0.60
     Waray
    0.60
    ISupport
    0.60
    Activations Density 0.002%

    No Known Activations