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. 16-GEMMASCOPE-RES-16K
    6. 5213
    Prev
    Next
    INDEX
    Explanations

    file paths and resource identifiers within code or markup

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Image file paths

    np_acts-logits-general · gemini-2.0-flash

    image paths and filenames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -1.40
     ModelExpression
    -1.22
    GraphicsUnit
    -1.16
     propOrder
    -1.16
     protoimpl
    -1.04
    rungsseite
    -1.00
    AddTagHelper
    -0.98
    principalTable
    -0.96
     समीक्षक
    -0.94
     EconPapers
    -0.94
    POSITIVE LOGITS
    icon
    0.65
    img
    0.60
     image
    0.58
     icon
    0.56
    ic
    0.54
    placeholder
    0.52
    logo
    0.52
    Icon
    0.52
     Image
    0.51
     images
    0.50
    Activations Density 0.080%

    No Known Activations