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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 8741
    Prev
    Next
    INDEX
    Explanations

    phrases related to Facebook account management and authentication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -1.06
     للاسماء
    -1.04
     noDo
    -1.01
     EconPapers
    -1.00
    
    -0.99
    GEBURTSDATUM
    -0.98
    rungsseite
    -0.96
    expandindo
    -0.92
     ModelExpression
    -0.91
    SequentialGroup
    -0.88
    POSITIVE LOGITS
     od
    0.40
     iz
    0.36
     pod
    0.36
     te
    0.35
     sad
    0.35
     na
    0.34
     i
    0.34
     pose
    0.33
     u
    0.32
     pri
    0.32
    Activations Density 0.110%

    No Known Activations