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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 59007
    Prev
    Next
    INDEX
    Explanations

    terms related to cement and cementation processes

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

    cement and its uses

    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
    対象
    -0.47
    shaw
    -0.46
     Auff
    -0.46
     righe
    -0.45
     Wesen
    -0.45
     CYTHON
    -0.45
    prek
    -0.44
     Starling
    -0.44
    ropathy
    -0.44
     Wau
    -0.44
    POSITIVE LOGITS
     Cement
    1.05
    Cement
    1.02
     cement
    1.00
    cement
    0.72
     cemented
    0.66
     cementerio
    0.57
    Cem
    0.56
     Cem
    0.55
     ciment
    0.53
    UrlResolution
    0.49
    Activations Density 0.006%

    No Known Activations