© 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. 34-GEMMASCOPE-RES-16K
    11. 13559
    Prev
    Next
    INDEX
    Explanations

    terms related to the color blue and its varying shades or contexts in descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Bakgrunnsstoff
    -0.45
    AutoField
    -0.44
    ConstraintMaker
    -0.41
    ViewFeatures
    -0.40
    tonsoft
    -0.39
     nakalista
    -0.39
    AndEndTag
    -0.38
     engraçadas
    -0.37
    ResponseWriter
    -0.37
     invokingState
    -0.36
    POSITIVE LOGITS
     blue
    2.81
     Blue
    2.59
    blue
    2.55
    Blue
    2.48
     BLUE
    2.44
    BLUE
    2.31
    蓝
    2.03
    藍
    2.00
     azul
    1.91
     blauen
    1.91
    Activations Density 0.391%

    No Known Activations