© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 4798
    Prev
    Next
    INDEX
    Explanations

    phrases related to user experience and sales enhancement in e-commerce

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.91
     unknownFields
    -0.72
     heretofore
    -0.68
     awfully
    -0.65
     wherewith
    -0.63
     forthwith
    -0.60
    /−
    -0.59
     prolly
    -0.58
     thence
    -0.58
     herewith
    -0.56
    POSITIVE LOGITS
     preuves
    0.80
     courants
    0.76
     picioare
    0.73
     segni
    0.73
     juridiques
    0.72
     rayures
    0.70
     économies
    0.70
     occhiali
    0.68
     larmes
    0.67
    .".
    0.66
    Activations Density 0.026%

    No Known Activations