© 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. 25-GEMMASCOPE-RES-16K
    11. 7537
    Prev
    Next
    INDEX
    Explanations

    instances of the word "express" and its variants, as well as words related to extremism and exploitation

    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
    fjspx
    -0.58
     executive
    -0.56
    TypedDataSet
    -0.56
    executive
    -0.55
     Мексичка
    -0.55
     expériment
    -0.54
     CreateTagHelper
    -0.54
    findpost
    -0.54
    Expert
    -0.53
     Audiodateien
    -0.53
    POSITIVE LOGITS
     viewDidLoad
    0.63
    IONS
    0.60
    perience
    0.58
    ventude
    0.55
    tagHelperRunner
    0.54
     Ră
    0.51
    ation
    0.51
    Orsay
    0.51
    treme
    0.49
     ciś
    0.49
    Activations Density 0.378%

    No Known Activations