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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 130976
    Prev
    Next
    INDEX
    Explanations

    terms related to permanence or durability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     springfox
    -0.66
    alakip
    -0.63
    KEYCODE
    -0.62
    MemoryWarning
    -0.58
    arangay
    -0.57
     getItemCount
    -0.57
    SharedDtor
    -0.56
    rungsseite
    -0.54
     disambiguazione
    -0.54
    ambién
    -0.53
    POSITIVE LOGITS
     Lasting
    0.85
    lasting
    0.82
     lasting
    0.79
     enduring
    0.64
     persistent
    0.56
    idespread
    0.54
     durable
    0.52
     longstanding
    0.50
     Persistent
    0.50
    ongoing
    0.50
    Activations Density 0.014%

    No Known Activations