© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1334
    Prev
    Next
    INDEX
    Explanations

    the conjunctions and connectors in sentences that suggest relationships or add additional information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Following "and"

    np_acts-logits-general · gemini-2.0-flash

    abstract concepts in lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    écri
    -0.39
     tää
    -0.38
     partout
    -0.38
    Síguenos
    -0.37
    ductos
    -0.36
     plupart
    -0.36
     BrowserRouter
    -0.35
    fromnode
    -0.35
     lijst
    -0.35
     boisson
    -0.34
    POSITIVE LOGITS
    ValueStyle
    0.81
     AssemblyTitle
    0.77
    extAlignment
    0.74
     snippetHide
    0.74
    TagMode
    0.71
    躇
    0.70
    tagHelperRunner
    0.70
    Vidite
    0.69
    OGND
    0.69
     nonatomic
    0.66
    Activations Density 0.357%

    No Known Activations