© 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. 23-GEMMASCOPE-RES-16K
    6. 6135
    Prev
    Next
    INDEX
    Explanations

    questions related to career decisions and educational pathways

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    嘩
    -0.48
     defStyleAttr
    -0.47
    atás
    -0.45
     divor
    -0.45
    MemoryWarning
    -0.45
    ่วน
    -0.44
    rž
    -0.42
     initialize
    -0.42
     gelang
    -0.41
     divorce
    -0.41
    POSITIVE LOGITS
     internship
    1.52
     internships
    1.42
     Internship
    1.26
     interns
    1.24
     intern
    1.23
     summer
    1.10
     placements
    1.09
     externs
    1.09
     placement
    1.05
    Intern
    1.01
    Activations Density 0.190%

    No Known Activations