© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 3838
    Prev
    Next
    INDEX
    Explanations

    JavaScript related functions and commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    官
    -0.43
    domain
    -0.42
    unik
    -0.42
    вень
    -0.42
    AspNetCore
    -0.41
     domain
    -0.41
    砖
    -0.41
    Ouest
    -0.41
    )?;
    -0.41
     compor
    -0.41
    POSITIVE LOGITS
     EconPapers
    0.90
     defaultstate
    0.89
     toggle
    0.86
     Audiodateien
    0.85
    toggler
    0.81
    ="@+
    0.81
     togg
    0.81
     ^=
    0.74
     estekak
    0.73
    toggle
    0.73
    Activations Density 0.088%

    No Known Activations