© 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. 9095
    Prev
    Next
    INDEX
    Explanations

    phrases indicating manipulation, subversion, and the triggering of unrest or dissent

    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
    Tikang
    -0.76
     ModelExpression
    -0.62
    httphttps
    -0.49
    HomeAsUpEnabled
    -0.48
     AttributeSet
    -0.48
    WriteTagHelper
    -0.47
    انيف
    -0.46
    /**
    -0.45
     Exacts
    -0.45
    KURZBESCHREIBUNG
    -0.45
    POSITIVE LOGITS
     estratégico
    0.49
    ThemeOverlay
    0.46
     tactic
    0.45
     psicológica
    0.45
    わざ
    0.41
     ligiloj
    0.41
    あえて
    0.40
    PAD
    0.39
     psicológico
    0.39
     purposely
    0.38
    Activations Density 0.829%

    No Known Activations