© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3731
    Prev
    Next
    INDEX
    Explanations

    references to investigations and related legal terms

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

    "investigation" or "investigate"

    np_acts-logits-general · gemini-2.0-flash

    investigation and related actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    <unused41>
    -0.82
    <unused42>
    -0.82
    <unused28>
    -0.82
    <pad>
    -0.82
    <unused43>
    -0.82
    <unused79>
    -0.82
    <unused74>
    -0.82
    <unused68>
    -0.82
    <unused52>
    -0.82
    <unused3>
    -0.81
    POSITIVE LOGITS
     investigation
    1.08
     investigate
    0.94
     investigations
    0.93
     investigating
    0.87
     INVESTIG
    0.86
     Investigation
    0.84
     INVESTIGATION
    0.81
     investigação
    0.79
     investigative
    0.78
     investigated
    0.78
    Activations Density 0.212%

    No Known Activations