© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 9170
    Prev
    Next
    INDEX
    Explanations

    comparisons indicated by the term "vs."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     okay
    -0.72
    okay
    -0.64
     أيضًا
    -0.58
    Okay
    -0.57
     anima
    -0.57
    ًا
    -0.55
     tille
    -0.53
    能够
    -0.53
     impor
    -0.52
     assi
    -0.52
    POSITIVE LOGITS
     Dept
    1.33
     Govt
    1.27
     Sgt
    1.27
     Assn
    1.24
     govt
    1.24
     Univ
    1.16
     Blvd
    1.16
    Sgt
    1.13
     Capt
    1.12
     Eqs
    1.11
    Activations Density 0.239%

    No Known Activations