© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 2993
    Prev
    Next
    INDEX
    Explanations

    phrases that express possession or experiences related to actions and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     krij
    -0.22
    ådet
    -0.22
    endforeach
    -0.21
     vinaigre
    -0.21
    kundige
    -0.21
     Aragón
    -0.20
     skrzy
    -0.20
     Black
    -0.19
    rildi
    -0.18
     diejenigen
    -0.18
    POSITIVE LOGITS
     '\\;'
    0.84
    цездатний
    0.80
    DockStyle
    0.76
     AssemblyVersion
    0.76
    IntoConstraints
    0.74
    ArrowToggle
    0.74
    المكان
    0.72
     فريبيس
    0.71
    脚注の使い方
    0.71
     Chwiliwch
    0.70
    Activations Density 0.594%

    No Known Activations