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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15172
    Prev
    Next
    INDEX
    Explanations

    phrases related to justification and evasion in arguments or discussions

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

    after quotations, dashes, or parentheses

    np_acts-logits-general · gemini-2.0-flash

    solving problems

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     ujednoznacz
    -0.63
     hObject
    -0.52
    hObject
    -0.52
    djangoproject
    -0.51
    帖最后由
    -0.50
    WireFormatLite
    -0.48
     newOwner
    -0.47
     snippetHide
    -0.46
    pompa
    -0.46
    invokeLater
    -0.46
    POSITIVE LOGITS
    Solution
    0.57
    solution
    0.54
     solution
    0.54
     SOLUTION
    0.51
     solutions
    0.50
     Lösung
    0.49
     Solution
    0.48
     solve
    0.47
    solutions
    0.47
     Lösungen
    0.46
    Activations Density 0.578%

    No Known Activations