Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 2883
    Prev
    Next
    INDEX
    Explanations

    references to the term "Mad" and related segments in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.50
     Normdatei
    -0.43
     testGet
    -0.43
     mouseClicked
    -0.40
     $_(
    -0.40
     ehemaligen
    -0.40
    pedo
    -0.38
     former
    -0.38
    IllegalArgument
    -0.37
    transQ
    -0.37
    POSITIVE LOGITS
     segment
    0.61
     increment
    0.59
    segment
    0.57
     Segment
    0.55
     enforce
    0.54
     span
    0.53
     implement
    0.48
    +#+
    0.48
     arrive
    0.48
    SEGMENT
    0.47
    Activations Density 0.213%

    No Known Activations