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. 9897
    Prev
    Next
    INDEX
    Explanations

    references to interconnectedness or the presence of relationships between individuals

    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
     gräns
    -0.68
     vectorielle
    -0.67
    leece
    -0.65
     ſaid
    -0.65
     Findlay
    -0.64
     gyerme
    -0.63
     Cline
    -0.62
     näin
    -0.60
     skär
    -0.60
     TAS
    -0.59
    POSITIVE LOGITS
    selves
    1.02
     AssemblyCulture
    1.02
    feinander
    0.83
    inander
    0.81
    parsedMessage
    0.79
     eachother
    0.79
     nhau
    0.78
     المعيارى
    0.77
     together
    0.76
    WireFormatLite
    0.75
    Activations Density 0.046%

    No Known Activations