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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4392
    Prev
    Next
    INDEX
    Explanations

    references to political figures and events in Honduras and the U.S

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

    specific names or references to political figures and their associated activities.

    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
    setVerticalGroup
    -0.54
     CreateTagHelper
    -0.54
     AssemblyCulture
    -0.52
    awtextra
    -0.47
     AssemblyTitle
    -0.44
    RotationOrder
    -0.41
     Mesin
    -0.40
     nonUne
    -0.40
    addPreferredGap
    -0.40
     szóci
    -0.40
    POSITIVE LOGITS
    Newly
    0.55
    newly
    0.51
     newly
    0.50
    ContentLoaded
    0.48
     neuem
    0.48
     new
    0.47
    nuevos
    0.46
     nuevos
    0.44
    autoreleasepool
    0.44
     yeni
    0.44
    Activations Density 0.282%

    No Known Activations