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-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 14971
    Prev
    Next
    INDEX
    Explanations

    instances of the word "suit" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     significant
    -0.41
     warning
    -0.40
    dostęp
    -0.39
     specific
    -0.38
     false
    -0.37
     digital
    -0.37
     policiales
    -0.35
     towards
    -0.34
     authored
    -0.34
     niyang
    -0.34
    POSITIVE LOGITS
    suit
    0.90
     Suit
    0.85
    Suit
    0.82
     suit
    0.78
    suits
    0.75
    TemporalType
    0.72
    tagHelperRunner
    0.70
     ruin
    0.69
     nahilalakip
    0.66
    WithIOException
    0.65
    Activations Density 0.214%

    No Known Activations