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. 16-GEMMASCOPE-RES-16K
    6. 12727
    Prev
    Next
    INDEX
    Explanations

    references to benefits and positive outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "benefit" or its variations

    np_acts-logits-general · gemini-2.0-flash

    benefit from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mashed
    -0.62
     mkdir
    -0.55
    Expensive
    -0.53
    yty
    -0.50
    olda
    -0.50
    beaten
    -0.48
    dymyr
    -0.48
    Lw
    -0.48
     Gub
    -0.47
     RestTemplate
    -0.47
    POSITIVE LOGITS
     benefits
    1.30
     benefit
    1.19
     Benefits
    1.19
    benefit
    1.16
     Benefit
    1.14
    Benefit
    1.13
     BENEFITS
    1.08
    benefits
    1.08
    Benefits
    1.08
     benefiting
    1.04
    Activations Density 0.117%

    No Known Activations