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. 20-GEMMASCOPE-RES-16K
    6. 7910
    Prev
    Next
    INDEX
    Explanations

    technical terms related to HTTP request and response headers

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

    Content-Type and Header information

    np_acts-logits-general · gemini-2.0-flash

    Content related headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.71
    DeleteBehavior
    -0.65
    RuleContext
    -0.54
    IComponent
    -0.53
     Bacteriol
    -0.52
    lorette
    -0.52
    CreateModel
    -0.51
     kasarigan
    -0.49
    سا
    -0.49
    (!__
    -0.48
    POSITIVE LOGITS
     headers
    0.76
     header
    0.75
     Content
    0.72
    header
    0.72
    Header
    0.72
    Content
    0.70
     HEAD
    0.67
    headers
    0.66
     Header
    0.65
     Accept
    0.64
    Activations Density 0.395%

    No Known Activations