© 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. 21-GEMMASCOPE-RES-16K
    11. 2980
    Prev
    Next
    INDEX
    Explanations

    terms related to internal mechanisms and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſind
    -0.84
     queſta
    -0.84
     pleaſure
    -0.83
    AndEndTag
    -0.81
    ValueStyle
    -0.81
    KommentareTeilen
    -0.81
     Majefty
    -0.78
     للمعارف
    -0.77
    aimeJ
    -0.77
    нгред
    -0.76
    POSITIVE LOGITS
     internal
    0.76
     external
    0.72
    External
    0.72
    Internal
    0.69
     Internal
    0.68
    external
    0.67
     externo
    0.66
     External
    0.66
    internal
    0.65
    INTERNAL
    0.60
    Activations Density 0.191%

    No Known Activations