© 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. 2-GEMMASCOPE-RES-16K
    6. 1894
    Prev
    Next
    INDEX
    Explanations

    references to tying or connections between concepts or entities

    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
    McKin
    -0.64
    Tikang
    -0.64
    errHandler
    -0.62
    findpost
    -0.62
     Dreyfus
    -0.61
     Mush
    -0.59
    ClientRect
    -0.59
    GOTREF
    -0.59
    sprechend
    -0.58
    Hul
    -0.57
    POSITIVE LOGITS
     tie
    3.47
     ties
    3.09
     tied
    3.05
     tying
    2.96
     Tie
    2.94
    Tie
    2.82
     Ties
    2.81
     Tied
    2.59
    Tied
    2.46
     TIE
    2.31
    Activations Density 0.055%

    No Known Activations