© 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. 31-GEMMASCOPE-RES-16K
    11. 14193
    Prev
    Next
    INDEX
    Explanations

    connections and comparisons between entities or concepts

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

    the phrase "vice versa" and related contrastive or reciprocal expressions.

    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
    thâu
    -0.42
    Aholisi
    -0.40
    ilités
    -0.35
     hasNext
    -0.35
    Wave
    -0.34
    InInspector
    -0.34
     reprints
    -0.34
     Wave
    -0.33
    PERTIES
    -0.33
     Pirate
    -0.33
    POSITIVE LOGITS
     vice
    3.50
     Vice
    2.63
     viceversa
    2.56
    vice
    2.53
    Vice
    2.53
     umgekehrt
    2.44
     VICE
    2.13
     conversely
    2.08
     vise
    2.05
     Conversely
    1.92
    Activations Density 0.334%

    No Known Activations