Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 2885
    Prev
    Next
    INDEX
    Explanations

    technical descriptions and specifications related to shapes and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    },[])
    -0.53
    liferay
    -0.50
    TextColor
    -0.47
    sika
    -0.44
    tainty
    -0.43
     betweenstory
    -0.42
     cellpadding
    -0.42
    ازم
    -0.42
     servos
    -0.41
     frosts
    -0.41
    POSITIVE LOGITS
     shape
    1.75
     shaped
    1.51
     Shape
    1.49
     shapes
    1.48
    shape
    1.44
     rounded
    1.37
     Shaped
    1.35
     SHAPE
    1.34
    shaped
    1.32
    Shape
    1.32
    Activations Density 0.490%

    No Known Activations