© 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. 16199
    Prev
    Next
    INDEX
    Explanations

    references to miscellaneous or unspecified items

    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
    MenuView
    -0.69
     "{{
    -0.67
    getCmp
    -0.63
     ExecuteAsync
    -0.61
    StoryboardSegue
    -0.59
     blusas
    -0.59
     озна
    -0.59
    Unmarshaller
    -0.58
    classNames
    -0.57
     Hedge
    -0.57
    POSITIVE LOGITS
     stuff
    3.84
     Stuff
    3.44
     STUFF
    3.21
    stuff
    3.20
    Stuff
    3.13
     stuffs
    2.61
    stuffs
    1.74
     crap
    1.52
     shit
    1.49
     stuffing
    1.48
    Activations Density 0.048%

    No Known Activations