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. 7752
    Prev
    Next
    INDEX
    Explanations

    function initialization sequences in code

    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
    tagext
    -0.53
    VolleyError
    -0.53
    LEGGI
    -0.52
    PMailer
    -0.51
     varandra
    -0.50
    ImageContext
    -0.50
     pecuni
    -0.48
     modelAndView
    -0.48
    $_['
    -0.48
     propOrder
    -0.48
    POSITIVE LOGITS
    init
    1.20
     init
    1.18
     Init
    1.12
    Init
    1.11
    INIT
    1.07
     Initialized
    1.05
     INIT
    1.04
     initi
    0.96
    initialise
    0.94
     Initi
    0.93
    Activations Density 0.076%

    No Known Activations