© 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 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. 11299
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to quantum physics and its applications

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

    Follows "a" and describes idealized systems or models

    np_acts-logits-general · gemini-2.0-flash

    models and systems

    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
    jooq
    -0.52
     defaultstate
    -0.52
    ParseTree
    -0.50
    astify
    -0.49
    +#+
    -0.48
     Convergence
    -0.47
    ropractor
    -0.47
     decrypted
    -0.46
    Palmar
    -0.46
    iffance
    -0.45
    POSITIVE LOGITS
     simple
    0.69
     idealized
    0.68
     model
    0.64
     ideal
    0.63
     simplest
    0.59
     systems
    0.59
    simple
    0.57
     models
    0.55
     situations
    0.55
    ideal
    0.54
    Activations Density 2.177%

    No Known Activations