© 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. 22-GEMMASCOPE-RES-16K
    6. 5666
    Prev
    Next
    INDEX
    Explanations

    HTML closing tags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.68
    rungsseite
    -0.63
     Infór
    -0.60
    HasAnnotation
    -0.60
    verwijspagina
    -0.59
     Audiodateien
    -0.59
     ſever
    -0.59
     wuß
    -0.57
     iſt
    -0.57
     ſch
    -0.57
    POSITIVE LOGITS
    RenderAtEndOf
    0.66
     AssemblyCulture
    0.54
    こんな
    0.35
    Enllaces
    0.34
     snippetHide
    0.34
    πως
    0.34
     aceste
    0.33
    WriteTagHelper
    0.33
    enumi
    0.32
     مشين
    0.32
    Activations Density 0.167%

    No Known Activations