© 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. 37-GEMMASCOPE-RES-16K
    11. 4733
    Prev
    Next
    INDEX
    Explanations

    expressions of personal emotions and introspection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yg
    -0.79
     ppl
    -0.69
     sth
    -0.69
     perciò
    -0.66
     Pls
    -0.63
     např
    -0.60
    Pls
    -0.60
     govt
    -0.56
     abt
    -0.56
     (=
    -0.55
    POSITIVE LOGITS
    Tikang
    0.73
    TagMode
    0.66
     pylint
    0.59
    ロウィン
    0.59
    しっかりと
    0.59
    нгред
    0.58
     impacting
    0.57
    >",
    0.56
    +:+
    0.55
     imagui
    0.55
    Activations Density 0.361%

    No Known Activations