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. 5-GEMMASCOPE-RES-16K
    6. 5152
    Prev
    Next
    INDEX
    Explanations

    specific numerical or statistical terms related to measurement and analysis

    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
     للمعارف
    -0.65
    фаль
    -0.50
    stava
    -0.48
    хь
    -0.47
    occuper
    -0.45
     externi
    -0.45
    chim
    -0.44
    Fns
    -0.44
    を外
    -0.43
    Бра
    -0.43
    POSITIVE LOGITS
    tagHelperRunner
    0.85
     stride
    0.80
    WriteTagHelper
    0.76
    djangoproject
    0.75
     betweenstory
    0.74
    createCanvas
    0.72
     JpaRepository
    0.71
     deductible
    0.71
    GenerationType
    0.71
    shadowRadius
    0.70
    Activations Density 0.976%

    No Known Activations