© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15598
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names or entities in a document

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

    following "Q:" or Roman letters

    np_acts-logits-general · gemini-2.0-flash

    English Gothic architecture

    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
    makeText
    -1.00
    Hozzáférés
    -0.83
    CloseOperation
    -0.81
    +#+#
    -0.81
    NameInMap
    -0.80
    
    -0.78
    ReusableCell
    -0.77
    VersionUID
    -0.77
    клопе
    -0.75
    principalColumn
    -0.74
    POSITIVE LOGITS
     houſe
    0.60
     δὲ
    0.55
     Houſe
    0.54
     Jefus
    0.54
     Chriftian
    0.53
     ftate
    0.53
     Chrift
    0.52
     μὲν
    0.50
     parezca
    0.49
     esfuer
    0.49
    Activations Density 0.078%

    No Known Activations