© 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. 3127
    Prev
    Next
    INDEX
    Explanations

    references to different layers and their characteristics in various contexts

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

    references to layering or layers in various contexts (e.g., photography, design, fabric, scientific processes).

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    references to layers or layering of materials.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered 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
     Goodwin
    -0.57
     OMITBAD
    -0.54
    habitude
    -0.53
     OnInit
    -0.52
    Com
    -0.50
    ußt
    -0.48
     sähkö
    -0.47
    anasia
    -0.46
    GOOD
    -0.46
    Credit
    -0.44
    POSITIVE LOGITS
     Layer
    1.40
     layer
    1.39
     LAYER
    1.27
    layer
    1.26
    Layer
    1.23
     Layers
    1.22
     layers
    1.21
    layers
    1.08
     layering
    1.04
    Layers
    1.02
    Activations Density 0.069%

    No Known Activations