© 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. 10-GEMMASCOPE-RES-16K
    6. 6884
    Prev
    Next
    INDEX
    Explanations

    steps or sequential instructions in a process or algorithm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prolific
    -0.53
    SerializeField
    -0.49
     onBind
    -0.48
    Ϣ
    -0.46
     populated
    -0.46
     mergeFrom
    -0.46
    arrant
    -0.45
     DBNull
    -0.45
    ugc
    -0.44
    discord
    -0.44
    POSITIVE LOGITS
     step
    2.05
    Step
    1.90
     Step
    1.89
    step
    1.84
     steps
    1.83
     Steps
    1.75
     STEP
    1.74
    Steps
    1.70
    STEP
    1.69
    steps
    1.67
    Activations Density 0.097%

    No Known Activations