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. 15999
    Prev
    Next
    INDEX
    Explanations

    references to materials in various contexts

    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
     propOrder
    -0.95
     Pseudomonas
    -0.94
    GraphicsUnit
    -0.91
     تضيفلها
    -0.89
     calendriers
    -0.85
    aventure
    -0.84
     Obre
    -0.83
     sequestration
    -0.80
     uncin
    -0.79
     cavitation
    -0.78
    POSITIVE LOGITS
     materials
    2.76
     Materials
    2.54
    materials
    2.47
    Materials
    2.41
     material
    2.37
     Material
    2.29
     MATERIALS
    2.23
     materiales
    2.17
     MATERIAL
    2.13
    MATERIAL
    2.13
    Activations Density 0.126%

    No Known Activations