© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 6799
    Prev
    Next
    INDEX
    Explanations

    occurrences of special characters and structured data formats within code snippets

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

    programming constructs and elements used in coding syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.79
     للاسماء
    -0.72
    principalColumn
    -0.71
    ########.
    -0.70
     domestiques
    -0.67
     Normdatei
    -0.63
    первых
    -0.61
    存于互联网档案馆
    -0.61
     '\\;'
    -0.59
     ویکی‌پدی
    -0.58
    POSITIVE LOGITS
     )
    0.64
     ]
    0.60
     ).
    0.59
     }
    0.55
     ),
    0.49
     kaynağından
    0.49
     ):
    0.48
     }{
    0.47
     hObject
    0.46
    ArrowToggle
    0.46
    Activations Density 0.364%

    No Known Activations