© 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. 10393
    Prev
    Next
    INDEX
    Explanations

    terms related to uniqueness and comparison to existing entities

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

    Modifying or adding to existing things

    np_acts-logits-general · gemini-2.0-flash

    existing, neighboring, other, new, nearby, actual

    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
    Personendaten
    -1.00
    SequentialGroup
    -0.90
    ロウィン
    -0.88
     fashiola
    -0.77
    <unused16>
    -0.76
    [@BOS@]
    -0.76
    <unused41>
    -0.76
    ſelben
    -0.76
    <unused51>
    -0.76
    <unused1>
    -0.76
    POSITIVE LOGITS
    .
    0.45
    ;
    0.34
    <eos>
    0.34
    ...
    0.31
     ibang
    0.29
    s
    0.28
     vertes
    0.28
    ..
    0.27
     diğer
    0.27
    Kapcsolódó
    0.27
    Activations Density 0.784%

    No Known Activations