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. 8-GEMMASCOPE-RES-16K
    6. 6031
    Prev
    Next
    INDEX
    Explanations

    terms related to noise, especially in the context of audio and its impact on communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.88
    Hentet
    -0.80
    opardy
    -0.70
    Халык
    -0.64
    UMBIA
    -0.63
    AddTagHelper
    -0.62
     Cristóbal
    -0.61
    acherous
    -0.61
    Personensuche
    -0.60
    Nationalité
    -0.59
    POSITIVE LOGITS
     neighbour
    0.58
     noise
    0.57
     neighbor
    0.57
     complaint
    0.53
     nuisance
    0.52
     annoyance
    0.50
     noisy
    0.50
    MethodManager
    0.48
    neighbour
    0.48
     complaints
    0.48
    Activations Density 0.202%

    No Known Activations