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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 84854
    Prev
    Next
    INDEX
    Explanations

    references to noise in various contexts

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

    noise characteristics and components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.42
     transfieras
    -0.38
     XXL
    -0.36
     triom
    -0.36
     Fä
    -0.35
     Swal
    -0.35
     aplican
    -0.33
    JsonProperty
    -0.33
    sqcup
    -0.33
    🔙
    -0.32
    POSITIVE LOGITS
     noise
    1.67
     Noise
    1.59
    Noise
    1.56
    noise
    1.52
     NOISE
    1.41
     ruido
    1.02
     noisy
    0.98
    噪
    0.96
     noises
    0.95
    噪音
    0.94
    Activations Density 0.021%

    No Known Activations