© 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. 21-GEMMASCOPE-RES-16K
    11. 2608
    Prev
    Next
    INDEX
    Explanations

    terms related to audio equipment, specifically microphones and their technical specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.73
    Билгалдахарш
    -0.62
    RegistryLite
    -0.61
    __':
    -0.59
    Itoa
    -0.57
     Audiodateien
    -0.55
    __":
    -0.53
     Roskov
    -0.53
    ecore
    -0.52
    cipar
    -0.51
    POSITIVE LOGITS
     microphone
    0.88
     mic
    0.78
     microphones
    0.78
     Microphone
    0.75
     condenser
    0.73
     mikrofon
    0.72
     mics
    0.70
    Microphone
    0.67
     Micro
    0.67
     Neumann
    0.67
    Activations Density 0.193%

    No Known Activations