© 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. 11966
    Prev
    Next
    INDEX
    Explanations

    references to specific genes, primers, or sequencing techniques in scientific contexts

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

    Sequences after the 5' end of a primer

    np_acts-logits-general · gemini-2.0-flash

    DNA primers

    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
     يتيمه
    -0.42
     kişilik
    -0.39
    ValueStyle
    -0.38
    rungsseite
    -0.36
     tight
    -0.36
    ỡng
    -0.35
     concept
    -0.35
     dictated
    -0.35
    삭
    -0.35
    マイズ
    -0.34
    POSITIVE LOGITS
    ChildScrollView
    0.51
     Infór
    0.47
     PropTypes
    0.46
    Annexes
    0.44
    utilisons
    0.44
     JpaRepository
    0.43
    SharedDtor
    0.43
    enetrable
    0.43
     Initialized
    0.41
     AspNetCore
    0.41
    Activations Density 0.328%

    No Known Activations