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. 6374
    Prev
    Next
    INDEX
    Explanations

    sentences that discuss issues or problems and their solutions

    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
     ohnehin
    -0.59
     odkazy
    -0.54
     bref
    -0.47
     sowieso
    -0.47
    Referanser
    -0.47
     yes
    -0.46
    就知道
    -0.46
    brief
    -0.45
    ThroughAttribute
    -0.45
     ogóle
    -0.44
    POSITIVE LOGITS
     Unfortunately
    2.05
     entanto
    1.99
    Unfortunately
    1.97
     however
    1.88
     unfortunately
    1.84
     However
    1.79
    However
    1.77
    unfortunately
    1.74
    however
    1.63
     problem
    1.57
    Activations Density 0.398%

    No Known Activations