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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 10085
    Prev
    Next
    INDEX
    Explanations

    terms related to sound and audio quality

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

    The token "sound" followed by a related word

    np_acts-logits-general · gemini-2.0-flash

    sound quality or source

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    autoIncrement
    -0.63
    ANP
    -0.55
     civiles
    -0.52
    ScopeManager
    -0.51
     Winding
    -0.51
     @"/
    -0.49
     rischio
    -0.49
     pajak
    -0.49
     Normdatei
    -0.49
    طني
    -0.49
    POSITIVE LOGITS
    tracks
    0.78
    bites
    0.77
    bite
    0.77
    proofing
    0.74
    board
    0.68
    proof
    0.67
     bites
    0.66
     bite
    0.65
    __':
    0.64
    lessly
    0.63
    Activations Density 0.070%

    No Known Activations