© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 15526
    Prev
    Next
    INDEX
    Explanations

    terms related to semi-structured methodologies or representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jurisdic
    -0.43
    องค์
    -0.43
    krieg
    -0.42
    zdro
    -0.41
    lebnis
    -0.41
    ACIONAL
    -0.41
    setList
    -0.40
     kasarigan
    -0.40
     poitrine
    -0.40
     citoy
    -0.40
    POSITIVE LOGITS
     semi
    2.92
     Semi
    2.86
    Semi
    2.73
    semi
    2.55
     sem
    2.55
     SEMI
    2.36
     Sem
    2.31
    Sem
    2.16
     semis
    2.05
    sem
    1.86
    Activations Density 0.157%

    No Known Activations