© 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. 11800
    Prev
    Next
    INDEX
    Explanations

    references to historical people and events

    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
     betweenstory
    -0.51
     unmittelbar
    -0.47
    <?
    -0.46
     personlig
    -0.44
     subsequently
    -0.44
     ベストアンサー
    -0.42
    anément
    -0.41
     vermitteln
    -0.41
     volgt
    -0.41
     samtidigt
    -0.41
    POSITIVE LOGITS
     thingy
    1.15
     dudes
    1.06
     freakin
    0.98
     dude
    0.98
     crappy
    0.96
     stuff
    0.95
     blah
    0.94
     yummy
    0.94
     pretty
    0.93
     freaking
    0.93
    Activations Density 1.059%

    No Known Activations