© 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. 25-GEMMASCOPE-RES-16K
    11. 7780
    Prev
    Next
    INDEX
    Explanations

    code-related functions and definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setLayoutManager
    -0.53
    ViewFeatures
    -0.52
     crescent
    -0.49
    olge
    -0.48
    ViewImports
    -0.47
     Thor
    -0.46
     BYU
    -0.45
     THOR
    -0.45
     graduating
    -0.44
     Sult
    -0.44
    POSITIVE LOGITS
     uLocal
    1.00
     iParam
    0.91
     bParam
    0.80
    iLocal
    0.77
     joaat
    0.76
    (&(
    0.72
     func
    0.71
     iLocal
    0.67
     iVar
    0.67
    iParam
    0.66
    Activations Density 0.076%

    No Known Activations