© 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. 12315
    Prev
    Next
    INDEX
    Explanations

    technical terminologies related to mechanisms and processes in scientific contexts

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

    technical or scientific descriptions in academic or patent documents.

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

    technical and scientific writing with specialized vocabulary and formal academic or patent language.

    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
    gucig
    -0.65
    survival
    -0.65
     sculpted
    -0.60
     centerline
    -0.60
     Aquaculture
    -0.60
    entendre
    -0.59
     demographics
    -0.59
     wildflowers
    -0.58
     lexicon
    -0.58
    retrie
    -0.58
    POSITIVE LOGITS
     conclusiones
    0.34
     fotográfica
    0.33
     fotográfico
    0.32
     investigaciones
    0.31
     elástica
    0.31
    mathfrak
    0.31
     antemano
    0.30
    \}\\
    0.30
     perfección
    0.29
     ​
    0.28
    Activations Density 0.740%

    No Known Activations