© 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. 34-GEMMASCOPE-RES-16K
    11. 1593
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss the impact of communication or rhetoric on beliefs and actions

    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
     both
    -0.80
     både
    -0.72
    both
    -0.63
     almost
    -0.57
     sekä
    -0.56
     rather
    -0.55
    而不是
    -0.54
     somewhat
    -0.54
    Both
    -0.52
    almost
    -0.51
    POSITIVE LOGITS
     nor
    2.25
     anymore
    2.03
    nor
    1.55
     anything
    1.49
     melainkan
    1.46
     tampoco
    1.44
     nemmeno
    1.38
     אלא
    1.35
    Nor
    1.29
     sondern
    1.29
    Activations Density 2.780%

    No Known Activations