© 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. 14005
    Prev
    Next
    INDEX
    Explanations

    references to command-line interfaces or commands

    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
    AddTagHelper
    -0.66
     pinulongan
    -0.48
    jaros
    -0.47
    __*/
    -0.46
    Hobbies
    -0.45
     Hutchison
    -0.44
     المعيارى
    -0.44
    hdys
    -0.44
     Vero
    -0.44
     slices
    -0.44
    POSITIVE LOGITS
     cli
    1.19
    cli
    1.15
    Cli
    1.05
     Cli
    1.02
     desperate
    0.88
    cliff
    0.80
     кли
    0.78
     panic
    0.77
     clip
    0.74
     clipping
    0.73
    Activations Density 0.284%

    No Known Activations