© 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. 24-GEMMASCOPE-RES-16K
    6. 11938
    Prev
    Next
    INDEX
    Explanations

    terms related to audio and sound effects

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

    "sound" or related to audio

    np_acts-logits-general · gemini-2.0-flash

    sound bites and effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -0.52
     getItemCount
    -0.49
     Roskov
    -0.49
    Бахар
    -0.49
    SEASON
    -0.48
    ANP
    -0.48
    getCount
    -0.47
    autoIncrement
    -0.47
     brancas
    -0.47
    sums
    -0.47
    POSITIVE LOGITS
    bites
    0.83
    tracks
    0.81
    bite
    0.79
    proofing
    0.77
    stage
    0.70
    tracked
    0.69
     bites
    0.69
    waves
    0.68
    cloud
    0.67
     bite
    0.65
    Activations Density 0.066%

    No Known Activations