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. 20-GEMMASCOPE-RES-16K
    6. 12086
    Prev
    Next
    INDEX
    Explanations

    elements related to marketing and branding strategies in products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Décès
    -0.48
    oa̍t
    -0.46
    serde
    -0.45
    zyż
    -0.43
    !*\
    -0.43
     concepto
    -0.43
     fVar
    -0.41
    CGRectMake
    -0.40
    ISF
    -0.40
    antwo
    -0.40
    POSITIVE LOGITS
     attention
    1.68
     Attention
    1.48
    attention
    1.45
    Attention
    1.43
     ATTENTION
    1.30
     Aufmerksamkeit
    1.22
     attract
    1.21
     attracting
    1.18
     conspicuous
    1.15
     attracts
    1.12
    Activations Density 0.239%

    No Known Activations