© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 14026
    Prev
    Next
    INDEX
    Explanations

    phrases related to experiences of intimacy and vulnerability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.57
    どうしても
    -0.53
    Sehr
    -0.52
     highly
    -0.49
    とっても
    -0.48
     sehr
    -0.48
     veldig
    -0.45
    Obviously
    -0.45
     extremely
    -0.45
     very
    -0.45
    POSITIVE LOGITS
     scarcely
    0.93
     едва
    0.93
     almost
    0.93
     practically
    0.91
     literalmente
    0.90
     literally
    0.88
     hardly
    0.86
    almost
    0.86
     downright
    0.84
    もはや
    0.83
    Activations Density 0.571%

    No Known Activations