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. 5-GEMMASCOPE-RES-16K
    6. 15719
    Prev
    Next
    INDEX
    Explanations

    instances of historical firsts or unique achievements

    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
     <=",
    -0.76
    ftagPool
    -0.76
    Aholisi
    -0.72
    #
    -0.72
     विश्वसनीयता
    -0.70
     يتيمه
    -0.68
    onViewCreated
    -0.67
     CreateTagHelper
    -0.67
     crdi
    -0.66
     Ophelia
    -0.66
    POSITIVE LOGITS
     who
    0.64
     jemals
    0.50
     ever
    0.48
    who
    0.47
    PageModule
    0.45
    titian
    0.44
     recently
    0.43
    дко
    0.41
     he
    0.41
     ayant
    0.41
    Activations Density 0.112%

    No Known Activations