© 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. 2-GEMMASCOPE-RES-16K
    6. 7691
    Prev
    Next
    INDEX
    Explanations

    terms and phrases associated with electrical and electronic components, as well as error codes in computing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rrggbb
    -0.62
    BagConstraints
    -0.49
    migrationBuilder
    -0.49
    WithIOException
    -0.47
    marvin
    -0.47
     (~(
    -0.47
    RectangleBorder
    -0.46
    Linki
    -0.46
     Minato
    -0.46
    interesting
    -0.46
    POSITIVE LOGITS
     Eb
    1.09
     É
    1.05
     EB
    1.03
     E
    1.01
     Eh
    1.00
     Eg
    1.00
     EA
    0.99
     Ey
    0.98
     Ek
    0.97
     EH
    0.97
    Activations Density 1.007%

    No Known Activations