© 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. 25-GEMMASCOPE-RES-16K
    11. 15664
    Prev
    Next
    INDEX
    Explanations

    expressions of belief and conviction 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 @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IUrlHelper
    -0.66
    AutoScaleMode
    -0.52
     CreateTagHelper
    -0.51
    MLLoader
    -0.51
    QMetaType
    -0.49
     ModelExpression
    -0.48
    publicPath
    -0.48
    ionage
    -0.48
    WireFormatLite
    -0.45
    گاب
    -0.45
    POSITIVE LOGITS
    FieldBuilder
    0.40
     croire
    0.40
     croit
    0.39
     believing
    0.38
     belief
    0.38
     Belief
    0.35
    ције
    0.35
    queryInterface
    0.35
     believed
    0.34
     investir
    0.34
    Activations Density 0.158%

    No Known Activations