Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5600
    Prev
    Next
    INDEX
    Explanations

    scientific measurements or results in the context of chemical analysis

    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
     consider
    -0.51
     personal
    -0.49
     si
    -0.49
     li
    -0.49
    inc
    -0.48
     Ari
    -0.48
     favor
    -0.47
     work
    -0.47
     E
    -0.47
    kut
    -0.46
    POSITIVE LOGITS
    ंदीखरीदारी
    0.86
     pinulongan
    0.85
    onViewCreated
    0.85
    ]")]
    0.81
     وتسجيلات
    0.80
    GEBURTSDATUM
    0.77
    CloseOperation
    0.76
     déput
    0.75
    skjaer
    0.74
     Lordships
    0.72
    Activations Density 0.223%

    No Known Activations