© 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. 14-GEMMASCOPE-RES-16K
    11. 7254
    Prev
    Next
    INDEX
    Explanations

    phrases related to potential criminal activities or suspicious circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     in
    -0.69
     -
    -0.61
     a
    -0.61
    ,
    -0.59
     de
    -0.58
     A
    -0.57
     
    -0.56
     as
    -0.56
    s
    -0.55
     and
    -0.55
    POSITIVE LOGITS
     Reſ
    1.30
     للاسماء
    1.25
     Efq
    1.25
    UnusedPrivate
    1.23
    GEBURTSDATUM
    1.22
     Anſ
    1.20
     myſelf
    1.19
     photolibrary
    1.19
     ſtate
    1.18
     Majefty
    1.17
    Activations Density 0.247%

    No Known Activations