© 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. 7-GEMMASCOPE-RES-16K
    11. 14436
    Prev
    Next
    INDEX
    Explanations

    verbs and expressions related to personal experiences and emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     outta
    -0.70
     gonna
    -0.60
     Aussie
    -0.57
     fuckin
    -0.56
    gotta
    -0.54
     wanna
    -0.53
     lotta
    -0.53
    Aussie
    -0.53
     gotta
    -0.53
    gonna
    -0.52
    POSITIVE LOGITS
    mektedir
    0.59
    maktadır
    0.52
     skall
    0.48
     cannot
    0.48
    uxxxx
    0.46
     destes
    0.41
     automóviles
    0.40
     입니다
    0.40
     sahiptir
    0.40
    Cannot
    0.40
    Activations Density 1.127%

    No Known Activations