Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 6458
    Prev
    Next
    INDEX
    Explanations

    terms related to speed, particularly emphasizing the word "fast."

    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
     AssemblyTitle
    -1.25
    LabelTagHelper
    -1.09
    rrggbb
    -1.08
     متعلقه
    -1.08
     propOrder
    -1.06
    SBATCH
    -1.06
    sidemargin
    -1.06
    numerusform
    -1.05
    aarrggbb
    -1.05
     murano
    -1.03
    POSITIVE LOGITS
     fast
    0.89
     Fast
    0.88
    -
    0.85
     FAST
    0.84
     low
    0.80
    fastjson
    0.79
    FAST
    0.79
     high
    0.79
     High
    0.78
     Low
    0.77
    Activations Density 0.089%

    No Known Activations