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. 10-GEMMASCOPE-RES-16K
    6. 4574
    Prev
    Next
    INDEX
    Explanations

    mathematical terminology and notation related to statistics and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.59
    MockMvc
    -0.55
    </b>
    -0.47
    NamedQueries
    -0.44
    eslint
    -0.43
    </i>
    -0.43
    Superclass
    -0.42
     south
    -0.42
    sieh
    -0.41
     sin
    -0.41
    POSITIVE LOGITS
    LookAnd
    0.94
     AssemblyCulture
    0.93
     gawas
    0.87
    MENAFN
    0.84
     OFDb
    0.82
    出版年
    0.78
     مشين
    0.78
    ituary
    0.78
    AndEndTag
    0.77
    évaluateur
    0.76
    Activations Density 2.700%

    No Known Activations