© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11136
    Prev
    Next
    INDEX
    Explanations

    comparative analyses and differences in study results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    datum
    -0.41
     Exacts
    -0.41
    verme
    -0.41
    manus
    -0.40
    muck
    -0.40
    biol
    -0.40
    crity
    -0.39
     Drapeau
    -0.39
    carl
    -0.39
    lwz
    -0.39
    POSITIVE LOGITS
     bessere
    0.46
    HomeAsUp
    0.46
     Unterschiede
    0.45
    <tfoot>
    0.44
    EndContext
    0.44
     differences
    0.43
     Differences
    0.42
     difference
    0.42
     besseren
    0.42
     better
    0.41
    Activations Density 0.423%

    No Known Activations