© 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. 20-GEMMASCOPE-RES-16K
    11. 5486
    Prev
    Next
    INDEX
    Explanations

    specific scientific or technical terminology related to biological and chemical processes

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

    scientific and technical terminology related to medical or biological processes.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    The neuron detects explanatory phrases about distinctive features or characteristics of entities, particularly in scientific, cultural, or historical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumii
    -0.40
     resourceCulture
    -0.40
     ne
    -0.34
    PostExecute
    -0.34
    лось
    -0.34
     simply
    -0.34
     Reiss
    -0.33
    Alike
    -0.33
     nemmeno
    -0.33
     small
    -0.32
    POSITIVE LOGITS
     kaarangay
    0.67
    sidemargin
    0.58
     незавершена
    0.55
     bezeichneter
    0.55
    CloseOperation
    0.52
     برانيه
    0.51
    ActionCreators
    0.51
     StringTokenizer
    0.50
    XtraReports
    0.49
    تقاوى
    0.49
    Activations Density 0.760%

    No Known Activations