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. 3090
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant issues or problems requiring attention

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

    Highlights preceding or following important statements/ideas

    np_acts-logits-general · gemini-2.0-flash

    introduced something special

    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
    InitVars
    -0.79
    Enllaces
    -0.71
    Geplaatst
    -0.56
     initComponents
    -0.53
    RefNanny
    -0.53
    \{\\
    -0.53
     autant
    -0.53
     autonomia
    -0.53
    出版年
    -0.52
    پیوند
    -0.52
    POSITIVE LOGITS
     something
    0.70
     another
    0.69
     special
    0.68
     CreateTagHelper
    0.67
    DoubleQuotes
    0.63
    +#+#
    0.62
    undrum
    0.58
    Something
    0.57
     unusual
    0.56
    XmlEnum
    0.55
    Activations Density 0.323%

    No Known Activations