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. 2146
    Prev
    Next
    INDEX
    Explanations

    elements related to data sources and their attributes

    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
     ProgressDialog
    -0.67
     pestaña
    -0.63
     tslint
    -0.57
     pytest
    -0.57
    SBATCH
    -0.56
     MainAxisSize
    -0.55
     onItemClick
    -0.54
     defStyleAttr
    -0.54
    merry
    -0.54
     ValidationError
    -0.54
    POSITIVE LOGITS
     source
    1.41
     Source
    1.35
    source
    1.31
     SOURCE
    1.27
    Source
    1.27
     sources
    1.05
    SOURCE
    1.05
    getSource
    1.00
    ource
    0.99
     Sources
    0.98
    Activations Density 0.140%

    No Known Activations