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. 45560
    Prev
    Next
    INDEX
    Explanations

    references to the telnet protocol and associated terms

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

    words starting with "tel"

    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
    evos
    -0.54
    mannian
    -0.53
     Italijanski
    -0.52
     للاسماء
    -0.52
    owan
    -0.52
    ++
    
    -0.52
    #--
    -0.51
    ȼ
    -0.51
     gus
    -0.51
     '\\;'
    -0.49
    POSITIVE LOGITS
     Tel
    1.02
    Tel
    0.99
     TEL
    0.94
     tel
    0.82
    TEL
    0.76
     Tél
    0.68
    tel
    0.67
     Telephone
    0.66
     tell
    0.64
     Tell
    0.64
    Activations Density 0.004%

    No Known Activations