© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 1523
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate comparisons or enhancements in quality or quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     very
    -1.04
     extremely
    -0.86
    very
    -0.86
     Very
    -0.85
     absolutely
    -0.82
    Very
    -0.82
     muy
    -0.81
     très
    -0.79
     totally
    -0.74
     foarte
    -0.74
    POSITIVE LOGITS
    ########.
    0.69
     ExecuteAsync
    0.62
    writeFieldEnd
    0.58
    fjspx
    0.58
    RegistryLite
    0.54
     initComponents
    0.50
    fromnode
    0.48
    اعمال
    0.48
     nahilalakip
    0.48
     rappresent
    0.47
    Activations Density 0.113%

    No Known Activations