© 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. 35-GEMMASCOPE-RES-16K
    11. 13727
    Prev
    Next
    INDEX
    Explanations

    technical terms related to devices and materials involved in electrical or mechanical systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    的原因
    -0.30
    enumi
    -0.28
    XX
    -0.27
     tartalomajánló
    -0.27
     None
    -0.26
    dd
    -0.25
    none
    -0.25
     насељу
    -0.25
    mml
    -0.24
     none
    -0.24
    POSITIVE LOGITS
     znajdu
    1.06
     belonging
    1.01
     owned
    1.00
     født
    0.98
     headquartered
    0.98
     originating
    0.98
     stationed
    0.97
     erected
    0.95
     inhabiting
    0.93
     installed
    0.92
    Activations Density 2.444%

    No Known Activations