© 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. 8-GEMMASCOPE-RES-16K
    6. 9279
    Prev
    Next
    INDEX
    Explanations

    lists or categories related to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.74
    +#+#
    -0.65
    InitVars
    -0.57
    WriteTagHelper
    -0.56
    DataAnnotations
    -0.55
    fjspx
    -0.55
    herin
    -0.53
     insuffisamment
    -0.53
     defStyleAttr
    -0.53
    tagHelperRunner
    -0.52
    POSITIVE LOGITS
    εια
    0.56
     otomatig
    0.56
    ustre
    0.55
     HttpNotFound
    0.53
    볍
    0.53
    лактика
    0.53
    sqcup
    0.52
    zoic
    0.52
    zoni
    0.52
     berdua
    0.51
    Activations Density 0.231%

    No Known Activations