© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 2211
    Prev
    Next
    INDEX
    Explanations

    instances of comparisons or differences in context or approach

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    indicating a difference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    esModule
    -0.56
    OGND
    -0.52
    ⇑
    -0.51
    舺
    -0.51
     ComVisible
    -0.51
     otomatig
    -0.50
    awaiter
    -0.50
     pouvoit
    -0.49
    guiente
    -0.49
    MessageTagHelper
    -0.49
    POSITIVE LOGITS
     than
    1.42
     altogether
    0.96
    than
    0.88
     niż
    0.85
     THAN
    0.84
     Than
    0.81
    Than
    0.81
     entirely
    0.80
     än
    0.74
     než
    0.74
    Activations Density 0.113%

    No Known Activations