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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 16165
    Prev
    Next
    INDEX
    Explanations

    strong emotional expressions and advice related to personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     therefore
    -0.76
    所以
    -0.74
     Therefore
    -0.71
     nedenle
    -0.67
    Therefore
    -0.66
     поэтому
    -0.66
     所以
    -0.65
     Derfor
    -0.65
     Поэтому
    -0.64
     Hence
    -0.64
    POSITIVE LOGITS
     متعلقه
    0.97
    rungsseite
    0.80
    Ведь
    0.80
     Normdatei
    0.79
    extAlignment
    0.78
    GraphicsUnit
    0.77
     كومونز
    0.75
    HasBeenSet
    0.74
     sinon
    0.72
    ंदीखरीदारी
    0.72
    Activations Density 0.413%

    No Known Activations