© 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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13950
    Prev
    Next
    INDEX
    Explanations

    terms related to data representation and analysis in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.90
     resourceCulture
    -0.79
     propOrder
    -0.73
     كومونز
    -0.65
     Chwiliwch
    -0.65
     otomatig
    -0.61
    StoryboardSegue
    -0.60
     CreateTagHelper
    -0.60
    EndContext
    -0.58
     snippetHide
    -0.57
    POSITIVE LOGITS
     greateſt
    0.39
     phénomènes
    0.32
     ouvriers
    0.32
    ſelf
    0.31
     leaſt
    0.31
    ſelves
    0.31
     fhew
    0.29
     bateaux
    0.29
     kathol
    0.28
     Gewerks
    0.28
    Activations Density 1.234%

    No Known Activations