© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 8461
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to programming and data structures

    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
     سكانية
    -1.23
     GenerationType
    -1.17
    tagHelperRunner
    -1.11
    principalTable
    -1.06
     snippetHide
    -1.04
     EconPapers
    -1.04
    Hentet
    -1.04
     виправивши
    -1.00
     kasarigan
    -1.00
    GeoNames
    -0.97
    POSITIVE LOGITS
    ),
    0.61
    )
    0.56
    的那种
    0.51
    さて
    0.39
     incidentally
    0.37
    )、
    0.36
    odd
    0.35
     )
    0.35
     (
    0.35
    的情况下
    0.35
    Activations Density 1.105%

    No Known Activations