Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 19-GEMMASCOPE-RES-16K
    6. 2983
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries about actions, intentions, and types

    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
     they
    -0.59
    makeText
    -0.59
     MainAxisSize
    -0.55
     Exactos
    -0.53
     he
    -0.52
    TagHelper
    -0.51
    they
    -0.49
    enumi
    -0.48
     it
    -0.47
    iget
    -0.47
    POSITIVE LOGITS
     did
    1.77
     does
    1.70
     do
    1.66
     Does
    1.40
     Did
    1.39
    Did
    1.32
    Does
    1.31
    did
    1.27
    does
    1.17
     Do
    1.10
    Activations Density 0.203%

    No Known Activations