© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 15433
    Prev
    Next
    INDEX
    Explanations

    repetitive phrases related to additional information or details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Autoritní
    -0.65
    AndroidJUnit
    -0.62
     nonUne
    -0.60
    GEBURTSDATUM
    -0.59
     oprot
    -0.58
     NSCoder
    -0.54
    蚪
    -0.54
    WriteTagHelper
    -0.54
    AISSEE
    -0.53
    bcryptjs
    -0.53
    POSITIVE LOGITS
     more
    3.13
    more
    2.58
    More
    2.41
     More
    2.39
     mehr
    2.30
     MORE
    2.20
     más
    2.20
     lebih
    2.16
     più
    2.06
    MORE
    2.00
    Activations Density 0.140%

    No Known Activations