© 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-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 7792
    Prev
    Next
    INDEX
    Explanations

    details related to academic and professional accomplishments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utuhkan
    -0.36
    ่ง
    -0.35
    leger
    -0.33
    lineWidth
    -0.32
    resizingMask
    -0.30
    glEnd
    -0.29
     mij
    -0.28
    umask
    -0.28
     cherchez
    -0.28
    Ouch
    -0.27
    POSITIVE LOGITS
     internship
    1.53
     internships
    1.47
     Internship
    1.33
     interns
    1.25
     intern
    1.20
    Intern
    1.05
     Intern
    1.02
    实习
    1.00
     summer
    1.00
     externs
    0.98
    Activations Density 0.285%

    No Known Activations