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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 7462
    Prev
    Next
    INDEX
    Explanations

    references to solid states or phases in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LabelTagHelper
    -0.93
    yntaxException
    -0.78
    Życiorys
    -0.75
     defaultstate
    -0.74
    InjectAttribute
    -0.70
    出版年
    -0.69
     Flix
    -0.67
     iParam
    -0.66
     paraphernalia
    -0.66
    InSection
    -0.65
    POSITIVE LOGITS
     solid
    3.07
    solid
    3.00
     Solid
    2.97
    Solid
    2.96
     SOLID
    2.83
    SOLID
    2.46
     solide
    2.16
     sólido
    2.16
     solids
    2.14
     solides
    2.06
    Activations Density 0.046%

    No Known Activations