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. 15-GEMMASCOPE-RES-16K
    6. 1288
    Prev
    Next
    INDEX
    Explanations

    instances of the word "whatever" and its variations in context

    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
    Datuak
    -0.87
     оригіналу
    -0.68
    BeginContext
    -0.68
    :^{
    -0.67
    TagMode
    -0.63
    AnchorStyles
    -0.63
     anise
    -0.61
     createSlice
    -0.61
    Pri
    -0.60
    doin
    -0.59
    POSITIVE LOGITS
    atever
    1.00
     Whatever
    0.95
     whatever
    0.86
    Whatever
    0.84
     apapun
    0.81
     Whoever
    0.81
     Hildebrand
    0.78
    whatever
    0.78
    Whoever
    0.77
     whoever
    0.77
    Activations Density 0.036%

    No Known Activations