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. 1588
    Prev
    Next
    INDEX
    Explanations

    references to GitHub URLs and repositories

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

    Mentioning the code repository "github"

    np_acts-logits-general · gemini-2.0-flash

    github urls

    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
    SIM
    -0.38
    DM
    -0.37
    MMS
    -0.36
    ாட
    -0.36
    
    -0.36
    str
    -0.35
     fine
    -0.35
     Hess
    -0.34
    MCS
    -0.34
     Passover
    -0.33
    POSITIVE LOGITS
    github
    1.55
     github
    1.30
    Github
    1.28
     Github
    1.17
     GitHub
    1.09
    GitHub
    1.03
    ITHUB
    0.94
    GITHUB
    0.91
    ithub
    0.84
    usercontent
    0.84
    Activations Density 0.077%

    No Known Activations