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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1300
    Prev
    Next
    INDEX
    Explanations

    key concepts related to communication and organization within projects

    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
     للاسماء
    -0.92
    LookAnd
    -0.85
    RenderAtEndOf
    -0.81
     Pourtant
    -0.78
     utafitiHapana
    -0.72
     mxArray
    -0.72
    IVEREF
    -0.72
    Tazama
    -0.72
     InputDecoration
    -0.71
    findpost
    -0.70
    POSITIVE LOGITS
     so
    2.31
     zodat
    2.10
     supaya
    1.66
    so
    1.63
     så
    1.54
     affinch
    1.46
     così
    1.44
     slik
    1.43
     afin
    1.43
     sehingga
    1.37
    Activations Density 0.901%

    No Known Activations