© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 30161
    Prev
    Next
    INDEX
    Explanations

    introductory markers or header elements in text

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

    playing a sound

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.60
    MergeFrom
    -0.57
    rophes
    -0.57
    Inspect
    -0.52
    ciled
    -0.51
    фото
    -0.51
    onnaissance
    -0.51
    ब्
    -0.50
    cognito
    -0.50
     inspection
    -0.49
    POSITIVE LOGITS
     AudioClip
    1.00
     sound
    0.96
     sounds
    0.90
     SOUND
    0.84
     Sound
    0.83
     AudioSource
    0.83
     MediaPlayer
    0.81
    sound
    0.81
     Sounds
    0.80
    sounds
    0.79
    Activations Density 0.032%

    No Known Activations