© 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. 0-GEMMASCOPE-RES-16K
    11. 2729
    Prev
    Next
    INDEX
    Explanations

    terms related to forgetting and sponsorship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.79
    хьтан
    -0.75
     enfans
    -0.71
    Jeografia
    -0.69
     мәкал
    -0.65
    舺
    -0.63
    oredCriteria
    -0.63
     Italij
    -0.63
     uſed
    -0.63
    rboles
    -0.62
    POSITIVE LOGITS
     forgotten
    0.89
     forget
    0.80
     forgot
    0.72
    forget
    0.68
     forgetting
    0.65
    forgotten
    0.64
     Forget
    0.60
     Forgotten
    0.60
    Forget
    0.57
     knowledge
    0.55
    Activations Density 0.255%

    No Known Activations