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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 15565
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating an increase or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.66
    johtaja
    -0.58
    UniformLocation
    -0.57
     ImageIcon
    -0.56
    openConnection
    -0.55
     TextAppearance
    -0.55
     NgModule
    -0.53
     aastal
    -0.52
     المعرف
    -0.52
    AFTA
    -0.51
    POSITIVE LOGITS
     importantly
    0.81
     than
    0.77
    igshid
    0.73
     likely
    0.69
     Audiodateien
    0.67
     often
    0.63
     Litt
    0.60
    vna
    0.59
     specifically
    0.59
     serious
    0.58
    Activations Density 0.161%

    No Known Activations