© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 38
    Prev
    Next
    INDEX
    Explanations

    descriptions of audio volume and sound levels

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

    loudness or volume

    np_acts-logits-general · gemini-2.0-flash

    volume and loudness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.61
     AspNetCore
    -0.59
    GIVEREF
    -0.56
     发表于
    -0.52
    ngdoc
    -0.51
    AddField
    -0.51
    filepath
    -0.51
    psies
    -0.49
    enumi
    -0.47
    +#+
    -0.47
    POSITIVE LOGITS
     louder
    1.47
     volume
    1.46
     loud
    1.42
     loudest
    1.30
    volume
    1.24
     volumen
    1.19
     volumes
    1.15
     loudly
    1.15
     Volume
    1.15
    loud
    1.12
    Activations Density 0.115%

    No Known Activations