© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 10824
    Prev
    Next
    INDEX
    Explanations

    discussions about accountability and responsibility in various contexts

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

    Text after conditional words ("if", "than")

    np_acts-logits-general · gemini-2.0-flash

    if then

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UrlResolution
    -0.56
    yntaxException
    -0.56
     gdyby
    -0.56
    tagHelperRunner
    -0.51
     näin
    -0.47
    afficheront
    -0.45
    BagConstraints
    -0.45
    setVerticalGroup
    -0.45
    WriteBarrier
    -0.44
    когда
    -0.43
    POSITIVE LOGITS
    ]")]
    0.65
     automatically
    0.57
     then
    0.48
    pso
    0.47
     surely
    0.46
     else
    0.46
     pretty
    0.45
     allora
    0.45
    automatically
    0.43
     heaven
    0.43
    Activations Density 0.550%

    No Known Activations