© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 581
    Prev
    Next
    INDEX
    Explanations

    programming concepts and terms related to APIs, file operations, and system calls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ^(@)
    -1.09
    ftance
    -1.08
    "):
    -1.08
    ftances
    -1.08
    ")){
    -1.05
     Wikimedijinoj
    -1.05
    '},
    -1.02
    "],
    -1.00
    iffion
    -1.00
    hematical
    -0.99
    POSITIVE LOGITS
    .
    0.76
    ,
    0.70
    )
    0.58
    »
    0.56
    </i>
    0.55
    ​
    0.55
    </h3>
    0.54
     |
    0.51
    </blockquote>
    0.51
     (
    0.50
    Activations Density 1.605%

    No Known Activations