© 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. 13712
    Prev
    Next
    INDEX
    Explanations

    academic and research affiliations related to environmental science and engineering

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

    preceding "Department", "School", or "College"

    np_acts-logits-general · gemini-2.0-flash

    academic department or school

    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
    harvard
    -0.51
    lccn
    -0.49
     try
    -0.45
     АН
    -0.44
    hoid
    -0.44
     sco
    -0.43
    Kaieteur
    -0.42
    Pfalz
    -0.41
     trying
    -0.41
    washingtonpost
    -0.41
    POSITIVE LOGITS
     School
    1.20
     Department
    1.15
    School
    1.10
     department
    1.03
    Department
    1.00
     Departments
    0.98
     departments
    0.92
     SCHOOL
    0.91
     Dept
    0.90
     DEPARTMENT
    0.90
    Activations Density 0.194%

    No Known Activations