© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 10939
    Prev
    Next
    INDEX
    Explanations

    geographic locations and landmarks

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

    location or direction

    np_acts-logits-general · gemini-2.0-flash

    locations and endpoints

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geplaatst
    -0.61
     мәкал
    -0.59
     resourceCulture
    -0.57
    Personendaten
    -0.54
    MemoryWarning
    -0.49
     Administrativna
    -0.48
    autoreleasepool
    -0.47
    脚注の使い方
    -0.46
    ंदीखरीदारी
    -0.45
    RTGC
    -0.45
    POSITIVE LOGITS
     towards
    0.81
     near
    0.80
     toward
    0.79
    toward
    0.74
     where
    0.72
    towards
    0.71
    near
    0.65
     Toward
    0.65
    Toward
    0.63
     nearest
    0.61
    Activations Density 0.540%

    No Known Activations