© 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. 3-GEMMASCOPE-RES-16K
    11. 6212
    Prev
    Next
    INDEX
    Explanations

    issues related to support and arguments in legal or social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.38
     siè
    -0.35
     ویکی‌پدیا
    -0.32
    ėjimo
    -0.31
     jadx
    -0.31
    chappen
    -0.26
    
    -0.25
     controversy
    -0.25
    IBOutlet
    -0.24
    FXMLLoader
    -0.24
    POSITIVE LOGITS
     linkovi
    0.69
    сылкі
    0.68
    Personendaten
    0.63
    httphttps
    0.63
    yours
    0.60
    Yours
    0.59
    TagMode
    0.59
     theirs
    0.59
    <?
    0.59
    RTEX
    0.57
    Activations Density 0.287%

    No Known Activations