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. 4-GEMMASCOPE-RES-16K
    6. 3147
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating relationships of size, quantity, or degree between entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.67
    érité
    -0.50
     față
    -0.49
    دور
    -0.48
    ensement
    -0.47
     QtCore
    -0.47
     faces
    -0.47
     PhpStorm
    -0.46
    /**
    -0.46
    четов
    -0.46
    POSITIVE LOGITS
     càng
    0.68
    وصلات
    0.62
    越高
    0.54
     дописавши
    0.53
     onResponse
    0.53
    ilsen
    0.53
     везе
    0.52
    越是
    0.52
    越大
    0.51
    CardContent
    0.50
    Activations Density 0.093%

    No Known Activations