© 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. 1939
    Prev
    Next
    INDEX
    Explanations

    references to schizophrenia and its associated health issues

    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
    MessageTagHelper
    -0.71
    aarrggbb
    -0.70
    EnableWeb
    -0.65
     springfox
    -0.62
    ButterKnife
    -0.61
    Portale
    -0.60
     AppBar
    -0.60
     <<<<<<<<<<<<<<
    -0.60
     initComponents
    -0.60
    uvwxyz
    -0.59
    POSITIVE LOGITS
    databind
    0.62
    IDENTAL
    0.58
    '},
    
    0.54
     rehab
    0.54
     Otherwise
    0.54
    chlor
    0.54
     servant
    0.52
    psf
    0.51
    })).
    0.51
     travellers
    0.50
    Activations Density 0.466%

    No Known Activations