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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12837
    Prev
    Next
    INDEX
    Explanations

    terms related to versatility and multifunctionality across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    astian
    -0.49
    ganu
    -0.46
    phrine
    -0.44
    mannian
    -0.44
    Snoo
    -0.44
    ethene
    -0.44
    hemiah
    -0.43
    Erreferentziak
    -0.42
    akterysty
    -0.42
    openha
    -0.42
    POSITIVE LOGITS
     mixed
    0.66
     hybrid
    0.61
     mix
    0.57
     versatile
    0.53
     mixte
    0.52
     mixta
    0.52
     hybrids
    0.50
     multitasking
    0.50
    混合
    0.49
     Mixed
    0.49
    Activations Density 0.480%

    No Known Activations