© 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. 7527
    Prev
    Next
    INDEX
    Explanations

    terms related to gene therapy and medical treatments involving virus vectors

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

    Follows "cti", often relating to medical terms

    np_acts-logits-general · gemini-2.0-flash

    keratoconjunctivitis activation deprivation survivability

    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
    клопе
    -0.44
    ایج
    -0.39
    Lamin
    -0.37
    ée
    -0.36
    ┈┈
    -0.36
    ]--;
    -0.35
     Besar
    -0.35
    leroi
    -0.35
     NUnit
    -0.34
    kaner
    -0.34
    POSITIVE LOGITS
    v
    1.02
    vi
    0.87
    ves
    0.83
    ved
    0.82
    vP
    0.80
    va
    0.78
    vis
    0.77
    ven
    0.76
    vile
    0.75
    ville
    0.75
    Activations Density 0.510%

    No Known Activations