© 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. 4-GEMMASCOPE-RES-16K
    11. 9971
    Prev
    Next
    INDEX
    Explanations

    terms related to noise and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     supérieurs
    -0.74
     bronce
    -0.72
     culturali
    -0.71
     originaux
    -0.70
     morire
    -0.69
     aukš
    -0.69
     seguintes
    -0.69
     Madsen
    -0.69
     postav
    -0.67
     actuels
    -0.66
    POSITIVE LOGITS
     noise
    2.57
     Noise
    2.43
     NOISE
    2.32
    Noise
    2.28
    noise
    2.15
     noises
    1.90
     noisy
    1.71
     ruido
    1.51
    noisy
    1.47
     ruidos
    1.37
    Activations Density 0.084%

    No Known Activations