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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 11618
    Prev
    Next
    INDEX
    Explanations

    references to social status and community dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.65
    lež
    -0.47
    hoeddwyd
    -0.45
     нале
    -0.45
    httphttps
    -0.44
    Демографія
    -0.44
    FormTagHelper
    -0.43
     no
    -0.43
    arthed
    -0.42
    lems
    -0.42
    POSITIVE LOGITS
     Efq
    0.70
     vaisselle
    0.66
    +#+#
    0.65
     asiatique
    0.64
    UnitTesting
    0.63
     Majefty
    0.63
     disambiguazione
    0.62
    didSet
    0.60
     Anſ
    0.59
     condomínio
    0.58
    Activations Density 0.124%

    No Known Activations