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. 10474
    Prev
    Next
    INDEX
    Explanations

    phrases that communicate motives or reasons behind actions and decisions

    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
     виправивши
    -0.87
    +#+#
    -0.71
    DockStyle
    -0.58
     समीक्षाओं
    -0.57
     bezeichneter
    -0.55
     IndexPath
    -0.55
     nahilalakip
    -0.55
    +#+
    -0.54
    mbggenerated
    -0.53
     IMDG
    -0.52
    POSITIVE LOGITS
    为什么要
    0.70
     purchase
    0.70
     why
    0.69
     buying
    0.65
    المشاركات
    0.64
     hire
    0.62
     buy
    0.60
    HasForeignKey
    0.57
     visit
    0.57
     pursue
    0.56
    Activations Density 0.429%

    No Known Activations