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. 8076
    Prev
    Next
    INDEX
    Explanations

    different types of bracketed method or function calls in programming code

    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
     Efq
    -0.76
     Harz
    -0.76
     MÁ
    -0.73
     Aoki
    -0.71
    jsonArray
    -0.71
     Bemer
    -0.70
    ς
    -0.69
     Sunil
    -0.68
     Daley
    -0.67
     Menlo
    -0.67
    POSITIVE LOGITS
    rillation
    0.94
     المعيارى
    0.82
    Portail
    0.80
    CORBA
    0.77
    ✨:
    0.77
    mopol
    0.77
     viewDidLoad
    0.76
     Wiktionnaire
    0.76
    \{\\
    0.75
     licences
    0.74
    Activations Density 0.216%

    No Known Activations