© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 14633
    Prev
    Next
    INDEX
    Explanations

    references to various types of noise and its impacts

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

    references to noise pollution or sound-related disturbances.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    words and contexts related to noise pollution and its effects.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HSSF
    -0.31
    WebControls
    -0.31
     stärken
    -0.29
    tagext
    -0.28
     twist
    -0.28
     mạch
    -0.27
    투
    -0.27
     înt
    -0.25
    errHandler
    -0.25
    ↹
    -0.25
    POSITIVE LOGITS
     noise
    2.88
     Noise
    2.55
    Noise
    2.47
    noise
    2.42
     NOISE
    2.34
     noisy
    2.33
     noises
    2.16
     ruido
    2.08
    noisy
    1.97
     ruidos
    1.87
    Activations Density 0.443%

    No Known Activations