© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 891
    Prev
    Next
    INDEX
    Explanations

    terms related to structural engineering and connections in devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Organisationen
    -0.37
     onCreateView
    -0.37
     betweenstory
    -0.36
    zkod
    -0.34
     lumineux
    -0.34
    KommentareTeilen
    -0.34
     alfombra
    -0.34
     autonomía
    -0.33
     esponja
    -0.33
     Wünsche
    -0.33
    POSITIVE LOGITS
     joints
    1.17
     welds
    1.13
     glue
    1.12
     seams
    1.11
     seam
    1.10
     suture
    1.08
     gluing
    1.07
     joint
    1.05
    glue
    1.05
     stitching
    1.05
    Activations Density 0.560%

    No Known Activations