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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 73691
    Prev
    Next
    INDEX
    Explanations

    aspects related to organizational collaboration and initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    tinyos
    -0.50
    SharedDtor
    -0.49
     noexcept
    -0.41
    outSlope
    -0.41
     poussière
    -0.40
    tagHelperRunner
    -0.40
    ContentAsync
    -0.40
    RotationOrder
    -0.36
    RTRS
    -0.35
    Cyfeiriadau
    -0.35
    POSITIVE LOGITS
     initiative
    0.71
    initiative
    0.62
     initiatives
    0.57
     Initiatives
    0.54
    Initiative
    0.53
    OGND
    0.50
    initi
    0.49
     INITI
    0.49
     Initiative
    0.48
     dramat
    0.48
    Activations Density 0.036%

    No Known Activations