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. 20-GEMMASCOPE-RES-16K
    6. 5211
    Prev
    Next
    INDEX
    Explanations

    terms related to digital technology and its applications in various fields

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

    before desirable outcomes

    np_acts-logits-general · gemini-2.0-flash

    improve and provide

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     exclusivamente
    -0.49
     langsung
    -0.49
     trực
    -0.48
    _
    -0.46
    가
    -0.45
    ))
    -0.44
    şim
    -0.42
    You
    -0.42
     plusieurs
    -0.41
     You
    -0.41
    POSITIVE LOGITS
     reduce
    0.94
     improve
    0.93
     provide
    0.90
     increase
    0.89
     Provide
    0.87
     reducing
    0.84
     promote
    0.83
    Provide
    0.83
     improves
    0.82
     enhance
    0.81
    Activations Density 0.365%

    No Known Activations