© 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. 14-GEMMASCOPE-RES-16K
    11. 11051
    Prev
    Next
    INDEX
    Explanations

    the word "that" in various contexts, indicating a strong focus on its usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⊱
    -0.37
     wanneer
    -0.37
    <bos>
    -0.36
     resistenza
    -0.36
    ériques
    -0.36
    ként
    -0.35
     miembro
    -0.35
     although
    -0.34
    xticks
    -0.34
     membro
    -0.34
    POSITIVE LOGITS
    AsUp
    1.06
    yntaxException
    0.99
    脚注の使い方
    0.95
    tagHelperRunner
    0.92
     AssemblyCulture
    0.91
    Демографія
    0.90
    zelfde
    0.90
    THAT
    0.90
     BrowserModule
    0.89
    ValueStyle
    0.89
    Activations Density 0.152%

    No Known Activations