© 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. 31-GEMMASCOPE-RES-16K
    11. 5625
    Prev
    Next
    INDEX
    Explanations

    phrases related to customer engagement and service explanations

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

    words and phrases that indicate conditional statements or hypothetical scenarios (e.g., "in case," "if," "when," "might," "should").

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.77
     estekak
    -0.76
     autorytatywna
    -0.72
    TagMode
    -0.72
     propOrder
    -0.70
     للاسماء
    -0.70
     Geſch
    -0.65
     Numerade
    -0.65
    WriteTagHelper
    -0.64
    WebServlet
    -0.60
    POSITIVE LOGITS
    ัฒ
    0.35
     Pe
    0.32
     presi
    0.31
     typ
    0.29
    lateinit
    0.28
     t
    0.28
     tri
    0.28
     Vol
    0.28
    вол
    0.28
    StartCoroutine
    0.27
    Activations Density 0.190%

    No Known Activations