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. 2-GEMMASCOPE-RES-16K
    6. 15062
    Prev
    Next
    INDEX
    Explanations

    terms related to the color gray or grey

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ISupport
    -0.77
    حوالہ
    -0.60
     propOrder
    -0.59
    BuildContext
    -0.56
     Evangelio
    -0.55
     semula
    -0.55
    fromCharCode
    -0.55
    DatabaseError
    -0.53
    nance
    -0.53
    сос
    -0.53
    POSITIVE LOGITS
     gray
    3.43
     grey
    3.20
    gray
    3.15
     Gray
    3.03
     Grey
    2.98
    Gray
    2.96
    grey
    2.88
    Grey
    2.86
     GRAY
    2.85
     GREY
    2.81
    Activations Density 0.045%

    No Known Activations