© 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. 6-GEMMASCOPE-RES-16K
    6. 11899
    Prev
    Next
    INDEX
    Explanations

    terms related to pain and body measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    poved
    -0.48
     palha
    -0.46
    Insee
    -0.46
    ZOOM
    -0.44
     gomma
    -0.44
     Crim
    -0.41
     denture
    -0.41
    readline
    -0.41
    spoken
    -0.40
     abuelos
    -0.40
    POSITIVE LOGITS
    StoryboardSegue
    0.94
     Neck
    0.91
    Shoulder
    0.89
     shoulders
    0.89
     jacket
    0.88
     Shoulder
    0.85
    Neck
    0.85
     Shoulders
    0.85
     viewDidLoad
    0.84
     abdomen
    0.84
    Activations Density 0.286%

    No Known Activations