© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 492
    Prev
    Next
    INDEX
    Explanations

    specific characteristics related to bodily features or conditions, often focusing on coloration, markings, and indicators of health or abnormalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /*
    -0.73
    ⓧ
    -0.67
     iprot
    -0.58
    #
    -0.57
    enumi
    -0.56
    StoryboardSegue
    -0.56
    ("/:
    -0.54
    balleur
    -0.51
    了口气
    -0.50
     betweenstory
    -0.50
    POSITIVE LOGITS
     spots
    1.21
     Spots
    1.07
    spots
    1.00
     spot
    0.95
    Spots
    0.95
     manchas
    0.87
     marks
    0.84
     mancha
    0.82
     Spot
    0.80
     stains
    0.80
    Activations Density 1.091%

    No Known Activations