© 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. 17-GEMMASCOPE-RES-16K
    11. 114
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and their structural formulas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.75
     MainAxisSize
    -0.59
    étisme
    -0.54
     Tenth
    -0.54
     tenth
    -0.53
     Twelfth
    -0.52
     intptr
    -0.52
     IFTT
    -0.51
     twelfth
    -0.51
     Muchos
    -0.51
    POSITIVE LOGITS
     three
    1.84
     trio
    1.76
    three
    1.66
     trois
    1.55
     Three
    1.53
    Three
    1.52
     ketiga
    1.48
     THREE
    1.47
     três
    1.45
    三人
    1.45
    Activations Density 0.959%

    No Known Activations