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. 10778
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to pH levels and their measurements in biological contexts

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

    Mentioning pH values or acidity/alkalinity

    np_acts-logits-general · gemini-2.0-flash

    pH values and acidity/alkalinity

    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
    abestanden
    -0.63
     متعلقه
    -0.54
    WithIdentifier
    -0.51
    INTS
    -0.49
     defaultstate
    -0.48
    SceneManagement
    -0.48
    tableFuture
    -0.48
     makeStyles
    -0.48
     golden
    -0.48
    DateTimeField
    -0.48
    POSITIVE LOGITS
     pH
    1.79
    pH
    1.58
     acidity
    1.27
     acidic
    1.22
     acid
    1.18
     Acid
    1.17
     alkaline
    1.12
    acid
    1.11
    Acid
    1.09
     alkalinity
    1.07
    Activations Density 0.514%

    No Known Activations