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. 7481
    Prev
    Next
    INDEX
    Explanations

    phrases related to data analysis and statistical references

    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
    存于互联网档案馆
    -0.79
     resourceCulture
    -0.75
    verwijspagina
    -0.69
     otomatig
    -0.66
     beginnetje
    -0.66
    fillType
    -0.65
    awtextra
    -0.64
     MainAxisSize
    -0.61
    AccessorTable
    -0.61
    PhysRev
    -0.60
    POSITIVE LOGITS
     how
    0.58
     anything
    0.56
     whether
    0.55
     that
    0.52
     something
    0.51
    :
    0.49
     what
    0.49
    ว่า
    0.49
    :✨
    0.47
     the
    0.46
    Activations Density 0.824%

    No Known Activations