© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 65005
    Prev
    Next
    INDEX
    Explanations

    instances of the word "thinning" or related forms indicating a reduction in thickness or density

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

    thin or thinning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     endfor
    -0.60
    RegressionTest
    -0.57
    뀜
    -0.57
    ніципа
    -0.55
     jacobs
    -0.54
     müſſen
    -0.52
    Rourke
    -0.52
     Doy
    -0.51
     loài
    -0.51
     evt
    -0.51
    POSITIVE LOGITS
     thinning
    1.65
    Thin
    1.52
     Thin
    1.52
     thin
    1.41
     thinned
    1.39
    thin
    1.38
     thinner
    1.34
    薄
    1.01
     thinly
    0.95
     dün
    0.87
    Activations Density 0.009%

    No Known Activations