Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 15558
    Prev
    Next
    INDEX
    Explanations

    terms related to audio effects and equipment

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

    "sound" or "tone" related words

    np_acts-logits-general · gemini-2.0-flash

    sound shaping

    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
    webElementXpaths
    -0.78
    ConstraintMaker
    -0.67
    లాలు
    -0.63
    Filmografia
    -0.61
    __(/*!
    -0.60
    ngilizce
    -0.60
     aktivitet
    -0.58
     seier
    -0.58
    Cubit
    -0.58
    isSuccessful
    -0.57
    POSITIVE LOGITS
     sound
    0.77
     tone
    0.76
     sounds
    0.72
     tones
    0.71
     sounding
    0.69
     warm
    0.68
     tonal
    0.67
     treble
    0.66
     subtle
    0.65
     weich
    0.65
    Activations Density 0.243%

    No Known Activations