© 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. 13524
    Prev
    Next
    INDEX
    Explanations

    repeated phrases, particularly articles and demonstratives, indicating focus on specific references in the text

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

    Followed by adjectives

    np_acts-logits-general · gemini-2.0-flash

    determiners followed by nouns

    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
     the
    -0.45
     
    -0.44
     parcialmente
    -0.35
     Widerspruch
    -0.35
     a
    -0.34
     Landwirtschaft
    -0.33
    The
    -0.33
    begin
    -0.32
     with
    -0.32
     Stufe
    -0.32
    POSITIVE LOGITS
    <unused43>
    1.09
    <unused41>
    1.09
    <unused16>
    1.09
    <unused28>
    1.09
    <unused3>
    1.09
    [@BOS@]
    1.09
    <unused8>
    1.09
    <unused14>
    1.09
    <unused51>
    1.09
    <unused52>
    1.09
    Activations Density 1.352%

    No Known Activations