© 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. 2600
    Prev
    Next
    INDEX
    Explanations

    phrases that express emotional states and interpersonal dynamics

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

    phrases and words expressing strong subjective feelings or commentary.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered 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
    ſelf
    -0.64
    IContainer
    -0.59
    évaluateur
    -0.56
    ckså
    -0.55
    gsmål
    -0.54
     dieux
    -0.53
    ſelves
    -0.52
    InputTagHelper
    -0.52
     interesa
    -0.51
     Taktlose
    -0.51
    POSITIVE LOGITS
     frequent
    0.82
     frequently
    0.79
     occasional
    0.73
     occasionally
    0.72
     whenever
    0.69
     Occasionally
    0.68
    Occasionally
    0.68
     periodic
    0.65
     Whenever
    0.65
     daily
    0.64
    Activations Density 0.283%

    No Known Activations