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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2-GEMMASCOPE-RES-16K
    6. 6172
    Prev
    Next
    INDEX
    Explanations

    references to the name "Michael."

    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
    endpush
    -0.61
    SOUNDBITE
    -0.59
    Oft
    -0.55
    Joseph
    -0.55
    ագրություններ
    -0.55
     Witherspoon
    -0.54
     gracia
    -0.53
     arqu
    -0.52
    ñoz
    -0.52
     Joseph
    -0.51
    POSITIVE LOGITS
     Michael
    1.00
    Michael
    0.96
     geographic
    0.92
    Geographic
    0.83
     geo
    0.83
     MICHAEL
    0.82
     geographical
    0.82
    geographic
    0.80
    MICHAEL
    0.79
    geo
    0.77
    Activations Density 0.046%

    No Known Activations