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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 90106
    Prev
    Next
    INDEX
    Explanations

    words related to packaging and organizational concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    zeera
    -0.42
     Fonten
    -0.41
    Cyfarwyddwr
    -0.41
    mostra
    -0.38
    irre
    -0.37
    <bos>
    -0.37
     negócios
    -0.37
    RTDA
    -0.36
    DebuggerNonUser
    -0.36
    OGND
    -0.36
    POSITIVE LOGITS
     pack
    1.21
     Pack
    1.18
    Pack
    1.16
     PACK
    1.13
    pack
    1.13
     Packs
    0.99
     packs
    0.98
    Packs
    0.98
     Packer
    0.97
    PACK
    0.95
    Activations Density 0.018%

    No Known Activations