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. 2292
    Prev
    Next
    INDEX
    Explanations

    references to healthcare programs and related organizational structures

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

    preceding "programme" or "program" (spelled differently)

    np_acts-logits-general · gemini-2.0-flash

    signalling pathway

    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
     tumors
    -1.09
     Tumors
    -1.08
     Ее
    -1.03
    Theater
    -0.98
    Еще
    -0.96
     theaters
    -0.94
     theater
    -0.93
    neighbors
    -0.93
     Theater
    -0.91
     Theaters
    -0.89
    POSITIVE LOGITS
     şi
    1.46
     organisations
    1.45
     utilisation
    1.43
    Ещё
    1.42
     unauthorised
    1.42
     generalised
    1.41
     Şi
    1.40
    Colours
    1.40
     organisational
    1.39
     fibres
    1.37
    Activations Density 0.525%

    No Known Activations