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. 15598
    Prev
    Next
    INDEX
    Explanations

    adverbs and phrases indicating certainty or frequency

    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
    Sod
    -0.63
     charging
    -0.62
     forgiven
    -0.62
     meda
    -0.62
     blooming
    -0.60
     shaking
    -0.59
     shaken
    -0.59
     nodding
    -0.59
     rectification
    -0.57
     Sod
    -0.57
    POSITIVE LOGITS
     have
    0.96
     had
    0.89
    verläs
    0.88
     gave
    0.87
    erdings
    0.86
     did
    0.85
    pfung
    0.83
     could
    0.80
    avía
    0.80
    tonode
    0.79
    Activations Density 0.281%

    No Known Activations