© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10853
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to biological and medical research, particularly focusing on cell types, assays, and genomic data

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

    Comes before "of", "is", "that" or a comparison word

    np_acts-logits-general · gemini-2.0-flash

    obtained data or credentials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ciela
    -0.47
     nisso
    -0.46
    ChildIndex
    -0.46
    हां
    -0.46
    uanya
    -0.42
    kmäler
    -0.41
    Vanjske
    -0.39
    ostic
    -0.39
    におすすめ
    -0.39
     posibil
    -0.38
    POSITIVE LOGITS
     obtained
    1.99
     created
    1.74
     produced
    1.74
     acquired
    1.68
    obtained
    1.68
     generated
    1.59
     purchased
    1.51
     issued
    1.50
     Obtained
    1.47
     supplied
    1.47
    Activations Density 2.221%

    No Known Activations