© 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. 11497
    Prev
    Next
    INDEX
    Explanations

    favorable attributes and interests related to simple pleasures and personal preferences

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

    like, prefer, enjoy

    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
    VersionUID
    -0.63
     disambiguazione
    -0.63
    protoimpl
    -0.59
    Personendaten
    -0.56
    帖最后由
    -0.56
    ChildScrollView
    -0.53
    IntoConstraints
    -0.53
    IContainer
    -0.52
     cập
    -0.51
     wykonania
    -0.51
    POSITIVE LOGITS
     Prefer
    0.38
    Prefer
    0.37
    prefer
    0.36
     symmetry
    0.34
    好きです
    0.33
     fancy
    0.32
    Jegyzetek
    0.31
    が好き
    0.31
     sim
    0.31
     preferring
    0.31
    Activations Density 0.033%

    No Known Activations