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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 8519
    Prev
    Next
    INDEX
    Explanations

    terms related to formal declarations or notifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.77
    Дереккөздер
    -0.76
    
    -0.76
    enumii
    -0.74
    ActionMode
    -0.72
    Personendaten
    -0.72
     AssemblyCulture
    -0.71
     незавершена
    -0.71
    SPATH
    -0.71
     fVar
    -0.70
    POSITIVE LOGITS
     issued
    1.11
     issuing
    1.05
     issuance
    1.00
     Issued
    0.99
     ISSUED
    0.98
    issued
    0.93
    Issued
    0.91
    emit
    0.87
     emitir
    0.87
     emiti
    0.85
    Activations Density 0.109%

    No Known Activations