© 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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8180
    Prev
    Next
    INDEX
    Explanations

    references to audio-related technologies and processes

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

    audio or sound

    np_acts-logits-general · gemini-2.0-flash

    audio recordings or messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     Abp
    -0.66
    WebVitals
    -0.65
     resourceCulture
    -0.64
     Reverso
    -0.61
    IndentedString
    -0.60
    digarh
    -0.60
    rrggbb
    -0.58
    __).
    -0.56
     OFDb
    -0.55
    adaptiveStyles
    -0.55
    POSITIVE LOGITS
    phile
    0.86
    visuel
    0.68
    ագրություններ
    0.66
    imageio
    0.66
    visual
    0.65
    VISUAL
    0.61
     recordings
    0.61
     clips
    0.59
     clip
    0.58
     recording
    0.58
    Activations Density 0.063%

    No Known Activations