© 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. 37-GEMMASCOPE-RES-16K
    11. 7970
    Prev
    Next
    INDEX
    Explanations

    instances of the word "need" and its variations, indicating a focus on necessity or requirement

    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
    {%
    -0.38
    ⓧ
    -0.34
    tolua
    -0.34
    RegressionTest
    -0.33
    cljs
    -0.32
    MENAFN
    -0.32
     being
    -0.31
    к
    -0.30
    ️
    -0.29
    ModelMap
    -0.29
    POSITIVE LOGITS
     urgente
    0.74
     dringend
    0.70
    iness
    0.69
     urgent
    0.68
     help
    0.66
     desesper
    0.65
     urgently
    0.63
    lessly
    0.62
     hjälp
    0.61
    SharedDtor
    0.60
    Activations Density 0.108%

    No Known Activations