© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8752
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "ak" in various forms, indicating a focus on that particular term or entity, possibly in a specific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.65
     Artes
    -0.61
     Langu
    -0.61
    Ferr
    -0.60
     Fiore
    -0.60
     Tf
    -0.57
     Amigo
    -0.57
     ché
    -0.56
     Busse
    -0.55
    はコチラ
    -0.54
    POSITIVE LOGITS
    ak
    3.16
    AK
    2.34
     Ak
    1.91
    Ak
    1.88
     ak
    1.85
    aks
    1.84
    akk
    1.72
     AK
    1.63
    aked
    1.52
    AKS
    1.44
    Activations Density 0.140%

    No Known Activations