© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 4833
    Prev
    Next
    INDEX
    Explanations

    technical terms and labels related to coding and mathematical functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ld
    -0.50
    providedIn
    -0.48
     Herder
    -0.47
    CDR
    -0.46
    Pd
    -0.46
    purl
    -0.46
     ArrayAdapter
    -0.46
    trl
    -0.46
     “
    -0.45
    ttf
    -0.44
    POSITIVE LOGITS
    x
    1.12
    ix
    1.00
    kx
    0.96
    ox
    0.96
    ax
    0.95
     Ax
    0.94
    tix
    0.92
     ax
    0.91
    ixx
    0.91
    rix
    0.90
    Activations Density 1.107%

    No Known Activations