© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 30175
    Prev
    Next
    INDEX
    Explanations

    expressions of enjoyment or surprise regarding books, particularly those with romance elements

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

    `I` followed by 'm, hope, was, or t

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.75
     conserv
    -0.56
    曖昧さ回避
    -0.54
    -------------</
    -0.54
    ]^{\
    -0.52
    "]();
    -0.51
    documented
    -0.51
    ]();
    -0.50
    forRoot
    -0.50
    Życiorys
    -0.50
    POSITIVE LOGITS
     Goodreads
    0.65
    NamedQueries
    0.61
     Majefty
    0.60
     Monfieur
    0.58
     Phry
    0.56
    fehlung
    0.56
    livro
    0.55
    ERRA
    0.55
    Goodreads
    0.54
     Afonso
    0.53
    Activations Density 0.161%

    No Known Activations