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. 12-GEMMASCOPE-RES-16K
    6. 45
    Prev
    Next
    INDEX
    Explanations

    references to previews and thumbnail images

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     getConnection
    -0.77
    andaş
    -0.71
    valbard
    -0.70
     hébergement
    -0.70
    GEBURTSDATUM
    -0.69
     bestaat
    -0.69
    ;">
    -0.68
    ocarditis
    -0.68
    BindView
    -0.68
     Hutchinson
    -0.68
    POSITIVE LOGITS
     preview
    1.01
     PREVIEW
    0.86
     Preview
    0.83
     previews
    0.82
     quiz
    0.79
     QUIZ
    0.77
     Peek
    0.77
     myſelf
    0.77
    Preview
    0.76
     trailer
    0.75
    Activations Density 0.127%

    No Known Activations