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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5102
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to components and systems in engineering or technology

    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
    IUrlHelper
    -0.67
    ManagedBean
    -0.59
    WaitGroup
    -0.59
    expandindo
    -0.56
    ragalactic
    -0.56
    AndroidJUnit
    -0.55
     estekak
    -0.55
    __(/*!
    -0.54
    UnusedPrivate
    -0.54
    LookAnd
    -0.53
    POSITIVE LOGITS
     méta
    0.43
    </thead>
    0.39
     évêque
    0.37
     asti
    0.36
     bébé
    0.35
    ########.
    0.34
     ſta
    0.34
     neceſſ
    0.34
     récompense
    0.33
    meta
    0.33
    Activations Density 0.836%

    No Known Activations