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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 77085
    Prev
    Next
    INDEX
    Explanations

    references to specific highways and routes

    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
    CardContent
    -0.47
     corne
    -0.45
    fjspx
    -0.43
    salm
    -0.43
    orre
    -0.42
    dome
    -0.41
    titleMargin
    -0.41
    AddTagHelper
    -0.40
    doma
    -0.40
    onomía
    -0.40
    POSITIVE LOGITS
     carreteras
    0.54
     sukienka
    0.51
     trám
    0.49
     Route
    0.49
     highways
    0.48
     parallèle
    0.48
     routes
    0.47
    県道
    0.46
     ModelExpression
    0.46
     roads
    0.46
    Activations Density 0.050%

    No Known Activations