© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4413
    Prev
    Next
    INDEX
    Explanations

    references to recording and capturing images or audio

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

    recording or capturing images/audio

    np_acts-logits-general · gemini-2.0-flash

    recording and capturing images/audio

    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
     ujednoznacz
    -0.54
    KeySpec
    -0.44
     fubject
    -0.44
    spesies
    -0.43
    mergeFrom
    -0.40
     ListTile
    -0.40
    mintaan
    -0.40
    +#+#
    -0.39
     nostru
    -0.39
     šķ
    -0.39
    POSITIVE LOGITS
     recording
    0.90
     capturing
    0.90
    recording
    0.87
     capture
    0.85
     Recording
    0.83
     RECORDING
    0.81
    Recording
    0.79
    capture
    0.77
     captures
    0.75
    Capture
    0.74
    Activations Density 0.500%

    No Known Activations