© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13075
    Prev
    Next
    INDEX
    Explanations

    phrases that express social or political commentary

    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
    localisation
    -0.59
    Personendaten
    -0.59
     InputDecoration
    -0.56
    LLocation
    -0.55
     EconPapers
    -0.55
     ligiloj
    -0.54
    illère
    -0.54
    @[+][
    -0.54
    HostException
    -0.53
    eneuve
    -0.53
    POSITIVE LOGITS
     indeed
    0.36
    <?
    0.35
    adpleegd
    0.35
     oftentimes
    0.33
     bahkan
    0.33
     connexe
    0.33
     Weisheit
    0.33
    indeed
    0.32
     thậm
    0.32
    прочем
    0.31
    Activations Density 0.146%

    No Known Activations