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. 3-GEMMASCOPE-RES-16K
    6. 6375
    Prev
    Next
    INDEX
    Explanations

    words related to specific terms and their meanings or definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hough
    -0.65
    ij
    -0.64
    "].
    -0.59
    ędz
    -0.58
    ]--;
    -0.58
    確認ください
    -0.57
    ECONDS
    -0.56
    ))\
    -0.56
     Riche
    -0.56
    anneau
    -0.55
    POSITIVE LOGITS
     term
    2.92
     Term
    2.83
     TERM
    2.67
    Term
    2.67
    term
    2.59
    TERM
    2.38
     término
    1.59
     terme
    1.57
     Terme
    1.25
     termo
    1.23
    Activations Density 0.102%

    No Known Activations