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. 2-GEMMASCOPE-RES-16K
    6. 1174
    Prev
    Next
    INDEX
    Explanations

    the relative pronoun "that"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.94
    adpleegd
    -0.92
    
    -0.82
    Демографія
    -0.82
     InputDecoration
    -0.80
    astify
    -0.79
    GetAxis
    -0.76
    yntaxException
    -0.75
     ainfi
    -0.75
     Monfieur
    -0.75
    POSITIVE LOGITS
     who
    1.52
    who
    1.17
     which
    0.91
     whose
    0.88
     Who
    0.81
     whom
    0.80
    Who
    0.78
     који
    0.78
     который
    0.76
     которые
    0.76
    Activations Density 0.450%

    No Known Activations