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. 12364
    Prev
    Next
    INDEX
    Explanations

    elements related to structured data and programming syntax

    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
     ExecuteAsync
    -0.56
    mybatisplus
    -0.54
     <<<<<<<<<<<<<<
    -0.52
    IBarButtonItem
    -0.52
    PYX
    -0.51
     OnInit
    -0.50
     BoxFit
    -0.50
    +:+
    -0.49
    kloped
    -0.48
    AddTagHelper
    -0.48
    POSITIVE LOGITS
     específicos
    0.41
     específica
    0.39
     poszczegól
    0.39
     jednotliv
    0.39
     específicas
    0.39
     jeweiligen
    0.38
     channels
    0.38
    WebpackPlugin
    0.38
    numbered
    0.36
     individuales
    0.36
    Activations Density 1.035%

    No Known Activations