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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 15-GEMMASCOPE-RES-16K
    6. 2284
    Prev
    Next
    INDEX
    Explanations

    infinitive verbs or phrases indicating intent or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     нео
    -0.51
    AnchorStyles
    -0.51
     fuga
    -0.49
     ample
    -0.49
    aminan
    -0.48
    Came
    -0.47
    weih
    -0.47
     persistent
    -0.46
     encouraging
    -0.45
    >{@
    -0.44
    POSITIVE LOGITS
    mybatisplus
    0.71
    expandindo
    0.70
    帖最后由
    0.69
    }]
    
    0.67
    Datuak
    0.65
    CloseOperation
    0.64
    sidemargin
    0.62
    MLLoader
    0.62
    WaitGroup
    0.62
    RegressionTest
    0.62
    Activations Density 0.230%

    No Known Activations