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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 16089
    Prev
    Next
    INDEX
    Explanations

    phrases indicating mechanical or technical issues

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

    DIY and troubleshooting

    np_acts-logits-general · gemini-2.0-flash

    DIY troubleshooting and advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.68
     automaticamente
    -0.62
    Bisous
    -0.59
     automáticamente
    -0.56
     lobby
    -0.54
     автоматически
    -0.54
     Lobby
    -0.53
     møte
    -0.53
     socially
    -0.53
     secretariat
    -0.52
    POSITIVE LOGITS
     DIY
    0.81
     troubleshooting
    0.65
     continúas
    0.63
     troubleshoot
    0.62
     aftermarket
    0.62
    DIY
    0.61
     warranty
    0.58
     Warranty
    0.57
     diy
    0.56
     overkill
    0.55
    Activations Density 0.184%

    No Known Activations