© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 3968
    Prev
    Next
    INDEX
    Explanations

    terms related to sound quality or audio production

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    taminophen
    -0.61
     fédé
    -0.58
     jspb
    -0.58
    RSpec
    -0.58
    Datuak
    -0.58
    mitives
    -0.56
    InjectMocks
    -0.56
    Jährige
    -0.56
     gynhyrchwyd
    -0.54
     Nunn
    -0.54
    POSITIVE LOGITS
     sound
    5.09
    sound
    4.50
     Sound
    4.45
    Sound
    4.33
     SOUND
    4.32
    SOUND
    3.69
     sounds
    3.49
     sounded
    3.24
     Sounds
    3.07
    sounds
    3.00
    Activations Density 0.065%

    No Known Activations