© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3827
    Prev
    Next
    INDEX
    Explanations

    emotionally charged dialogue or expressions of vulnerability

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

    Followed by an action verb

    np_acts-logits-general · gemini-2.0-flash

    person followed by action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pointing
    -0.53
     pleaſure
    -0.51
     waving
    -0.51
    zap
    -0.49
     strolling
    -0.48
     stroll
    -0.48
    jahtera
    -0.48
     shouting
    -0.47
    Walking
    -0.46
    一脸
    -0.46
    POSITIVE LOGITS
    SourceChecksum
    0.82
    ंदीखरीदारी
    0.69
    
    0.68
    دانشنامهٔ
    0.68
    GenerationType
    0.66
     Réponses
    0.65
    UnitTesting
    0.64
    DoubleQuotes
    0.63
    Personendaten
    0.63
    webElementXpaths
    0.63
    Activations Density 0.106%

    No Known Activations