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. 3624
    Prev
    Next
    INDEX
    Explanations

    the word "However" indicating a contrast or exception

    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
    InputTagHelper
    -0.80
     doInBackground
    -0.76
     ***!
    -0.75
    ########.
    -0.74
    hyrchwyd
    -0.73
     Cæsar
    -0.71
     figliu
    -0.71
     resume
    -0.70
     nakalista
    -0.70
     ویکی‌پدیا
    -0.69
    POSITIVE LOGITS
    drawString
    0.65
    ing
    0.63
    pleft
    0.61
    μβρίου
    0.61
     bottes
    0.60
     However
    0.59
     HUR
    0.56
     Indep
    0.56
    gly
    0.56
     Tras
    0.56
    Activations Density 0.121%

    No Known Activations