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. 1-GEMMASCOPE-RES-16K
    6. 7018
    Prev
    Next
    INDEX
    Explanations

    constructs related to memory and data structure management in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HasFactory
    -0.64
    StoryboardSegue
    -0.63
    OrBuilder
    -0.60
     Wikispecies
    -0.59
     jspb
    -0.57
    NOPQRST
    -0.55
    sizeCache
    -0.55
     snippetHide
    -0.55
     وسلم
    -0.54
    istos
    -0.53
    POSITIVE LOGITS
    󠁣
    0.60
     חיצוניים
    0.58
    naments
    0.54
    conio
    0.52
    windowFixed
    0.52
    amentals
    0.51
     lockers
    0.50
     spiegel
    0.49
    lète
    0.49
    wyt
    0.48
    Activations Density 0.728%

    No Known Activations