© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 12169
    Prev
    Next
    INDEX
    Explanations

    variations of the word "over" and related terms indicating excess or abundance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FormTagHelper
    -0.34
     chaves
    -0.31
     chave
    -0.29
    BRACKET
    -0.29
     câu
    -0.28
    tijds
    -0.28
    რი
    -0.28
     אות
    -0.28
     gezicht
    -0.27
     Giá
    -0.27
    POSITIVE LOGITS
     Over
    0.75
     препратки
    0.71
    Over
    0.69
    󠁴
    0.65
    OVER
    0.64
     ब्रेकडाउन
    0.63
     OVER
    0.61
     overla
    0.60
     Sobre
    0.60
    overs
    0.60
    Activations Density 0.412%

    No Known Activations