© 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. 19-GEMMASCOPE-RES-16K
    11. 10946
    Prev
    Next
    INDEX
    Explanations

    elements related to online forums and discussions, including post references and links

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tikang
    -0.83
    SizeF
    -0.74
    isContained
    -0.71
    JspWriter
    -0.71
    AndEndTag
    -0.69
     '\\;'
    -0.65
    TagMode
    -0.64
    numerusform
    -0.64
    webElement
    -0.63
    consulté
    -0.63
    POSITIVE LOGITS
     thread
    1.81
     Thread
    1.51
     threads
    1.49
    Thread
    1.45
    thread
    1.43
     THREAD
    1.35
     topic
    1.25
     Threads
    1.25
    Threads
    1.23
     Topic
    1.12
    Activations Density 0.137%

    No Known Activations