© 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. 40-GEMMASCOPE-RES-16K
    11. 1151
    Prev
    Next
    INDEX
    Explanations

    phrases related to censorship and suppression of speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageTagHelper
    -0.44
    OGND
    -0.44
    LookAnd
    -0.43
     melding
    -0.42
    +:+
    -0.40
     vastly
    -0.39
     Taras
    -0.38
     majeurs
    -0.37
    VYMaps
    -0.37
    setVerticalGroup
    -0.37
    POSITIVE LOGITS
     tribal
    0.61
     mediocrity
    0.57
     primitive
    0.55
    Tribal
    0.53
     impunity
    0.53
     inferiority
    0.51
     foolishness
    0.51
     blackmail
    0.51
    tribal
    0.50
     stupidity
    0.49
    Activations Density 0.216%

    No Known Activations