© 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. 6803
    Prev
    Next
    INDEX
    Explanations

    character traits and behaviors of individuals in various contexts

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

    personality traits or character descriptions that convey individual qualities and dispositions.

    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
     onData
    -0.52
    ImageContext
    -0.48
     joaat
    -0.40
    pired
    -0.39
     getIs
    -0.39
    marginVertical
    -0.38
    rrggbb
    -0.38
     testé
    -0.38
     sust
    -0.37
    gerufen
    -0.36
    POSITIVE LOGITS
     approach
    0.70
     minded
    0.61
     thinker
    0.60
     abordagem
    0.58
     Approach
    0.57
     nature
    0.56
    ness
    0.56
    approach
    0.56
     thinkers
    0.56
    Approach
    0.55
    Activations Density 0.346%

    No Known Activations