© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 120471
    Prev
    Next
    INDEX
    Explanations

    expressions and themes related to interpersonal relationships and emotional connections

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

    following common continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     obec
    -0.41
     correctes
    -0.41
    ۜ
    -0.40
    綬
    -0.39
    ensen
    -0.38
     BitmapFactory
    -0.38
    ulipas
    -0.38
    xlabel
    -0.38
     istore
    -0.37
     tans
    -0.37
    POSITIVE LOGITS
     very
    0.69
     quite
    0.57
     much
    0.57
     zijne
    0.56
     extremely
    0.55
    CrossRef
    0.54
     considerable
    0.53
     less
    0.51
     매우
    0.50
     considerably
    0.50
    Activations Density 0.094%

    No Known Activations