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

    Neuronpedia

    APICircuit 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. 18-GEMMASCOPE-RES-16K
    6. 10224
    Prev
    Next
    INDEX
    Explanations

    terms related to polymers, their structures, and associated features in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.97
    UnusedPrivate
    -0.88
    Cyfarwyddwr
    -0.81
    FieldBuilder
    -0.81
    Personensuche
    -0.75
     "..\..\..\
    -0.75
    AddTagHelper
    -0.75
     الحره
    -0.73
     "..\..\
    -0.72
    󠁿
    -0.72
    POSITIVE LOGITS
     dedans
    0.77
     dessus
    0.48
     drin
    0.45
     مشين
    0.45
     it
    0.41
    ony
    0.39
     nyingi
    0.39
     nela
    0.37
     فيه
    0.37
     thereon
    0.36
    Activations Density 0.605%

    No Known Activations