© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 58199
    Prev
    Next
    INDEX
    Explanations

    mentions of "Cedar," likely in reference to a specific location or object related to the text

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

    Cedar or Caesar

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    remadura
    -0.37
    AppContext
    -0.36
    <i>
    -0.36
    mbangan
    -0.34
    Info
    -0.34
    <strong>
    -0.33
    www
    -0.32
    <em>
    -0.32
    newInstance
    -0.32
    -0.32
    POSITIVE LOGITS
    +#+
    0.91
     Cedar
    0.90
     Caesar
    0.87
     cedar
    0.86
    Cedar
    0.83
    cedar
    0.82
     Cæsar
    0.82
    Caesar
    0.80
     Caesars
    0.79
     Cesar
    0.77
    Activations Density 0.004%

    No Known Activations