© 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. 12011
    Prev
    Next
    INDEX
    Explanations

    statements reflecting opinions or beliefs regarding age and understanding

    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
     poveznice
    -0.46
     Erzä
    -0.36
    inence
    -0.35
    ouson
    -0.35
    ItemBackground
    -0.35
     atmospheres
    -0.34
     urme
    -0.34
    ownie
    -0.34
    responseCode
    -0.33
    requireNonNull
    -0.33
    POSITIVE LOGITS
     ignorance
    1.45
     ignorant
    1.30
     Ignorance
    1.17
     clueless
    1.16
     uneducated
    1.07
    不懂
    1.05
     knowledge
    1.02
     unaware
    0.99
     illiterate
    0.98
     understanding
    0.97
    Activations Density 0.583%

    No Known Activations