© 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. 7618
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental and governmental regulations, particularly in medical and financial contexts

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

    preceding "Research", "Protection", or "Faculty"

    np_acts-logits-general · gemini-2.0-flash

    domain specific phrases

    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
     here
    -0.54
     just
    -0.54
    ,
    -0.54
     along
    -0.52
    رامی
    -0.52
     that
    -0.51
     this
    -0.51
     more
    -0.50
     jari
    -0.50
     then
    -0.50
    POSITIVE LOGITS
    #+#
    0.91
    новниш
    0.82
     '\\;'
    0.81
     Walkover
    0.77
     Мексичка
    0.72
    Personendaten
    0.71
    <()>
    0.69
     تانيه
    0.68
    UIControlState
    0.67
    LookAnd
    0.67
    Activations Density 0.564%

    No Known Activations