© 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. 11-GEMMASCOPE-RES-16K
    11. 9530
    Prev
    Next
    INDEX
    Explanations

    phrases indicating inclination or tendencies in behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.49
     Caruso
    -0.46
     miljö
    -0.44
     Anſ
    -0.44
     anſ
    -0.44
    ImageIO
    -0.43
    VersionUID
    -0.43
     myſelf
    -0.42
     equival
    -0.41
     препратки
    -0.41
    POSITIVE LOGITS
     tend
    1.39
     tends
    1.38
     tended
    1.26
     tienden
    1.22
     tendency
    1.18
    tend
    1.10
     cenderung
    1.09
     tending
    1.07
     tiende
    1.05
     TEND
    1.02
    Activations Density 0.291%

    No Known Activations