© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-GEMMASCOPE-RES-16K
    11. 9003
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize limitations or restrictions related to achieving specific goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تانيه
    -0.45
    bellum
    -0.40
    primitive
    -0.39
    primitives
    -0.38
    Primitive
    -0.38
     défend
    -0.37
    ndes
    -0.36
     pity
    -0.36
     modernisation
    -0.36
    筆
    -0.35
    POSITIVE LOGITS
    elemField
    0.56
    istoitu
    0.54
    と思ったら
    0.52
     suddenly
    0.51
    Personendaten
    0.50
    참고
    0.50
     resourceCulture
    0.50
    Suddenly
    0.49
    RegressionTest
    0.48
     unexpectedly
    0.48
    Activations Density 0.374%

    No Known Activations