© 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. 10734
    Prev
    Next
    INDEX
    Explanations

    names and related terms associated with food and cooking

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

    Uncommon or made-up names

    np_acts-logits-general · gemini-2.0-flash

    Hawaiian names and related words

    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
     Administrativna
    -0.73
     []:
    -0.68
    ########.
    -0.65
    TagMode
    -0.59
    __':
    -0.59
    GEBURTSDATUM
    -0.57
    Rhestr
    -0.56
     createState
    -0.53
    rungsseite
    -0.50
     contextLoads
    -0.50
    POSITIVE LOGITS
     betweenstory
    0.51
    intre
    0.46
     McAllister
    0.45
    ➯
    0.43
    alii
    0.42
    eringer
    0.42
    eren
    0.42
    eringen
    0.41
     unangemessene
    0.41
    another
    0.41
    Activations Density 1.144%

    No Known Activations