© 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. 30-GEMMASCOPE-RES-16K
    11. 14920
    Prev
    Next
    INDEX
    Explanations

    personal growth and self-discovery themes

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

    followed by forms of "to know" or "to realize"

    np_acts-logits-general · gemini-2.0-flash

    realize and recognize

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ヌーピー
    -0.35
     gü
    -0.35
     Predic
    -0.34
     predic
    -0.33
     advising
    -0.32
    strategia
    -0.32
    illem
    -0.32
     كورة
    -0.32
    rbrakk
    -0.32
     anzub
    -0.32
    POSITIVE LOGITS
     realize
    1.46
     realization
    1.41
     realizing
    1.41
     realise
    1.34
     realisation
    1.34
     realising
    1.30
     realizes
    1.29
     realized
    1.27
     recognize
    1.23
     recognizing
    1.22
    Activations Density 0.464%

    No Known Activations