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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 10770
    Prev
    Next
    INDEX
    Explanations

    CSS display properties related to block elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     royaume
    -0.45
     Fleetwood
    -0.42
     soldat
    -0.41
     armée
    -0.41
    iseur
    -0.40
     navideña
    -0.39
     venía
    -0.39
    \{\\
    -0.39
     Keuangan
    -0.38
    apimachinery
    -0.38
    POSITIVE LOGITS
    AsUp
    0.62
    Personendaten
    0.59
     defaultstate
    0.58
     clearfix
    0.55
     block
    0.49
    DockStyle
    0.45
    webElementXpaths
    0.45
    Diwedd
    0.45
    block
    0.44
     BLOCK
    0.44
    Activations Density 0.003%

    No Known Activations