© 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. 35-GEMMASCOPE-RES-16K
    11. 7989
    Prev
    Next
    INDEX
    Explanations

    key terms related to interpersonal interactions, particularly in the context of interviews and relationships

    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
    为例
    -0.64
     versehen
    -0.57
    Бахар
    -0.55
    IUrlHelper
    -0.53
    حوالہ
    -0.53
     utafitiHapana
    -0.52
     propOrder
    -0.50
    httphttps
    -0.50
    titleMargin
    -0.50
     BoxDecoration
    -0.49
    POSITIVE LOGITS
     with
    2.88
     dengan
    1.65
     với
    1.55
     avec
    1.53
    with
    1.52
     עם
    1.44
    กับ
    1.37
     kanssa
    1.34
     With
    1.29
    With
    1.22
    Activations Density 6.509%

    No Known Activations