© 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. 6001
    Prev
    Next
    INDEX
    Explanations

    nuanced discussions around regulatory effects within biological systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical or analytical language related to categories, types, and systematic comparisons.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
    uxxxx
    -0.94
     surla
    -0.91
     snippetHide
    -0.85
     שוליים
    -0.82
    GEBURTSDATUM
    -0.82
    rungsseite
    -0.76
    httphttps
    -0.76
    OGND
    -0.70
     autorytatywna
    -0.68
    AddTagHelper
    -0.68
    POSITIVE LOGITS
     different
    0.64
     types
    0.63
     styles
    0.56
    Different
    0.52
     Different
    0.49
     diferentes
    0.48
     forskjellige
    0.47
     distintos
    0.47
     unterschied
    0.47
     type
    0.45
    Activations Density 0.687%

    No Known Activations