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. 10-GEMMASCOPE-RES-16K
    6. 2927
    Prev
    Next
    INDEX
    Explanations

    references to excessive quantities or levels of various substances, particularly in a biological or ecological context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tableFuture
    -0.60
    BeginContext
    -0.59
    Datuak
    -0.58
     Wikispecies
    -0.57
    ]!=
    -0.54
    setPreferred
    -0.54
    organised
    -0.54
    adaptiveStyles
    -0.54
     Jdbc
    -0.54
    vatar
    -0.54
    POSITIVE LOGITS
     excessive
    1.00
     exces
    0.99
    Excessive
    0.94
     excès
    0.94
     Excessive
    0.92
     excess
    0.90
     excesso
    0.88
     exceso
    0.87
     overdo
    0.85
     overflow
    0.83
    Activations Density 0.275%

    No Known Activations