© 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. 8255
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to programming, data analysis, and scientific research methodologies

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

    following specific symbols or letters

    np_acts-logits-general · gemini-2.0-flash

    analysis of components and their properties

    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
    The
    -0.30
     “
    -0.26
     The
    -0.25
    A
    -0.23
     ‘
    -0.23
     libremente
    -0.21
     tokoh
    -0.21
    Don
    -0.21
    current
    -0.21
     fuese
    -0.21
    POSITIVE LOGITS
     manipulation
    1.06
     evaluation
    1.04
     analysis
    1.03
     simplification
    1.03
     optimisation
    1.02
     deployment
    1.02
     maximization
    1.02
     optimization
    1.02
     removal
    1.01
     identification
    1.00
    Activations Density 1.523%

    No Known Activations