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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8466
    Prev
    Next
    INDEX
    Explanations

    statistical terminology and components related to scientific experiments or analyses

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

    Tokens before descriptive words like "increased", "decreased", or "higher"

    np_acts-logits-general · gemini-2.0-flash

    higher, lower, increased, decreased

    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
     MainAxisSize
    -0.66
    UVWXYZ
    -0.59
    +#+#
    -0.58
     disambiguazione
    -0.50
    сылкі
    -0.50
     aDecoder
    -0.48
     صوتيه
    -0.48
     cdr
    -0.47
     ARP
    -0.47
     EPO
    -0.45
    POSITIVE LOGITS
     tendencia
    0.81
     trend
    0.78
     tended
    0.73
     excepción
    0.71
     showed
    0.70
     tendency
    0.65
     тенден
    0.64
     marginally
    0.64
     trends
    0.63
     Tenden
    0.63
    Activations Density 4.722%

    No Known Activations