© 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. 12476
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical analysis and noise in data

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

    phrases related to noise, errors, or artifacts in scientific measurements or data.

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

    words and phrases related to noise, error, and uncertainty in scientific measurements and data analysis.

    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
    出版年
    -0.47
    TypedDataSet
    -0.47
    EndContext
    -0.47
     Roskov
    -0.45
     parted
    -0.44
     ModelExpression
    -0.44
    ftagPool
    -0.42
    rungsseite
    -0.41
     Asser
    -0.41
    MouseAdapter
    -0.41
    POSITIVE LOGITS
     contamination
    0.78
     noise
    0.77
     errors
    0.73
     contamin
    0.72
     spurious
    0.71
     inaccuracies
    0.68
     artifacts
    0.68
     effects
    0.67
     unavoidable
    0.66
     artefacts
    0.65
    Activations Density 3.109%

    No Known Activations