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. 8-GEMMASCOPE-RES-16K
    6. 4588
    Prev
    Next
    INDEX
    Explanations

    phrases and descriptors related to structures or boundaries that enclose or surround something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     referenties
    -0.66
    SuppressLint
    -0.66
    MigrationBuilder
    -0.65
     boisson
    -0.60
     незавершена
    -0.57
    createTextNode
    -0.54
    antMatchers
    -0.52
     storica
    -0.52
    PBT
    -0.50
     prestar
    -0.50
    POSITIVE LOGITS
     surrounding
    0.97
     circumference
    0.97
     enclosing
    0.97
     surround
    0.96
     perimeter
    0.88
     surrounded
    0.85
     вокруг
    0.83
     surrounds
    0.83
     circum
    0.82
     around
    0.81
    Activations Density 0.357%

    No Known Activations