© 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. 27-GEMMASCOPE-RES-16K
    11. 8079
    Prev
    Next
    INDEX
    Explanations

    phrases related to compensation and balancing factors in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/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.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    통
    -0.33
     continuation
    -0.32
     Running
    -0.31
     Continuation
    -0.31
    inguém
    -0.31
     통
    -0.31
     Моло
    -0.31
    停止
    -0.31
     foreign
    -0.30
     Rear
    -0.30
    POSITIVE LOGITS
     compensate
    1.60
     compensating
    1.57
     compensated
    1.45
     compens
    1.44
    compens
    1.41
     Compens
    1.35
     compensatory
    1.32
     compensation
    1.30
    compensation
    1.23
     компен
    1.18
    Activations Density 0.373%

    No Known Activations