© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105566
    Prev
    Next
    INDEX
    Explanations

    references to nylon and related synthetic materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cuerdo
    -0.40
     dikem
    -0.39
     ار
    -0.39
     heureuse
    -0.37
    }=
    -0.36
    }}=
    -0.35
    gefügt
    -0.35
     chegada
    -0.34
     hjer
    -0.34
     rów
    -0.34
    POSITIVE LOGITS
     Nylon
    1.31
     nylon
    1.27
    Nylon
    1.25
    nylon
    1.22
     setPassword
    0.76
     pageSize
    0.71
     Velcro
    0.70
     newUser
    0.69
     velcro
    0.68
    zzleHttp
    0.68
    Activations Density 0.005%

    No Known Activations