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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 5933
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to server configuration and handling requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
     generalised
    -0.96
     neighbouring
    -0.94
     recognised
    -0.92
     learnt
    -0.91
     behavioural
    -0.91
     personalised
    -0.90
    coloured
    -0.89
     behaviour
    -0.89
     optimised
    -0.89
     tumour
    -0.88
    POSITIVE LOGITS
     Afterward
    0.67
     favorably
    0.66
    Theater
    0.66
     flavorful
    0.66
     favorite
    0.64
     favors
    0.64
     ๆ
    0.64
    favorite
    0.63
     geologic
    0.63
    Favorite
    0.63
    Activations Density 3.417%

    No Known Activations