© 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. 15-GEMMASCOPE-RES-16K
    6. 2248
    Prev
    Next
    INDEX
    Explanations

    specific geographic locations and biodiversity references within ecological contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Israel
    -0.38
    IsPostBack
    -0.37
    JCheckBox
    -0.36
     Pass
    -0.35
     enfans
    -0.34
     fooling
    -0.34
    ỡi
    -0.33
     Sha
    -0.33
     Brit
    -0.32
     Hebrew
    -0.31
    POSITIVE LOGITS
    تقاوى
    0.66
     CanadaChoose
    0.65
     Vietnamese
    0.65
    Vietnam
    0.63
    Vietnamese
    0.62
     Vietnam
    0.61
     vietnam
    0.58
    IntoConstraints
    0.58
    Autoritní
    0.57
     Saigon
    0.56
    Activations Density 0.086%

    No Known Activations