Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 2031
    Prev
    Next
    INDEX
    Explanations

    instances of the word "in" as well as 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 @ 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
     Roskov
    -1.06
     RIPRODUZIONE
    -0.81
     betweenstory
    -0.79
    InitVars
    -0.78
    [++
    -0.76
    MemoryWarning
    -0.71
    archiviato
    -0.70
     referrerpolicy
    -0.70
    shadowOpacity
    -0.69
    thâu
    -0.69
    POSITIVE LOGITS
    In
    1.07
     In
    0.96
    At
    0.93
     At
    0.84
    On
    0.84
     وفي
    0.82
     On
    0.73
    During
    0.73
    For
    0.72
    Within
    0.70
    Activations Density 0.377%

    No Known Activations