© 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. 12893
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication and contacting individuals or entities

    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
     <=",
    -0.59
     dépens
    -0.50
     Taktlose
    -0.49
    PTION
    -0.49
    IndentedString
    -0.48
    Against
    -0.48
    èlement
    -0.47
     Against
    -0.47
    illance
    -0.47
    contribution
    -0.46
    POSITIVE LOGITS
     about
    1.10
     regarding
    1.08
     directly
    1.06
     personally
    0.93
     privately
    0.91
    regarding
    0.90
     concerning
    0.87
    about
    0.84
     Directly
    0.84
     directement
    0.83
    Activations Density 0.296%

    No Known Activations